Weakly_Supervised
-
Stress Estimation in Elderly Oncology Patients Using Visual Wearable Representations and Multi-Instance Learning
2026-04-08 12:06:21Ioannis Kyprakis, Vasileios Skaramagkas, Georgia Karanasiou, Vasilis Bouratzis, Andri Papakonstantinou, Dimitar Stefanovski, Kalliopi Keramida, Aristofania Simatou, Ketti Mazzocco, Anastasia Constantinidou, Konstantinos Marias, Dimitrios I. Fotiadis, Manolis TsiknakisAbstract
Psychological stress is clinically relevant in cardio-oncology, yet it is typically assessed only through patient-reported outcome measures (PROMs) and is rarely integrated into continuous cardiotoxicity surveillance. We estimate perceived stress in an elderly, multicenter breast cancer cohort (CARDIOCARE) using multimodal wearable data from a smartwatch (physical activity and sleep) and a chest-worn ECG sensor. Wearable streams are transformed into heterogeneous visual representations, yielding a weakly supervised setting in which a single Perceived Stress Scale (PSS) score corresponds to many unlabeled windows. A lightweight pretrained mixture-of-experts backbone (Tiny-BioMoE) embeds each representation into 192-dimensional vectors, which are aggregated via attention-based multiple instance learning (MIL) to predict PSS at month 3 (M3) and month 6 (M6). Under leave-one-subject-out (LOSO) evaluation, predictions showed moderate agreement with questionnaire scores (M3: R^2=0.24, Pearson r=0.42, Spearman rho=0.48; M6: R^2=0.28, Pearson r=0.49, Spearman rho=0.52), with global RMSE/MAE of 6.62/6.07 at M3 and 6.13/5.54 at M6.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06990
PDF
-
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
2026-04-08 02:49:19Yaqi Zhao, Haoliang Sun, Yating Wang, Yongshun Gong, Yilong YinAbstract
Prompt learning has gained significant attention as a parameter-efficient approach for adapting large pre-trained vision-language models to downstream tasks. However, when only partial labels are available, its performance is often limited by label ambiguity and insufficient supervisory information. To address this issue, we propose Holistic Optimal Label Selection (HopS), leveraging the generalization ability of pre-trained feature encoders through two complementary strategies. First, we design a local density-based filter that selects the top frequent labels from the nearest neighbors' candidate sets and uses the softmax scores to identify the most plausible label, capturing structural regularities in the feature space. Second, we introduce a global selection objective based on optimal transport that maps the uniform sampling distribution to the candidate label distributions across a batch. By minimizing the expected transport cost, it can determine the most likely label assignments. These two strategies work together to provide robust label selection from both local and global perspectives. Extensive experiments on eight benchmark datasets show that HopS consistently improves performance under partial supervision and outperforms all baselines. Those results highlight the merit of holistic label selection and offer a practical solution for prompt learning in weakly supervised settings.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06614
PDF
-
PASTA: Vision Transformer Patch Aggregation for Weakly Supervised Target and Anomaly Segmentation
2026-04-07 08:29:11Melanie Neubauer, Elmar Rueckert, Christian RauchAbstract
Detecting unseen anomalies in unstructured environments presents a critical challenge for industrial and agricultural applications such as material recycling and weeding. Existing perception systems frequently fail to satisfy the strict operational requirements of these domains, specifically real-time processing, pixel-level segmentation precision, and robust accuracy, due to their reliance on exhaustively annotated datasets. To address these limitations, we propose a weakly supervised pipeline for object segmentation and classification using weak image-level supervision called 'Patch Aggregation for Segmentation of Targets and Anomalies' (PASTA). By comparing an observed scene with a nominal reference, PASTA identifies Target and Anomaly objects through distribution analysis in self-supervised Vision Transformer (ViT) feature spaces. Our pipeline utilizes semantic text-prompts via the Segment Anything Model 3 to guide zero-shot object segmentation. Evaluations on a custom steel scrap recycling dataset and a plant dataset demonstrate a 75.8% training time reduction of our approach to domain-specific baselines. While being domain-agnostic, our method achieves superior Target (up to 88.3% IoU) and Anomaly (up to 63.5% IoU) segmentation performance in the industrial and agricultural domain.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09701
PDF
-
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
2026-04-07 08:14:48Shoaib Sadiq Salehmohamed, Jinal Prashant Thakkar, Hansika Aredla, Shaik Mohammed Omar, Shalmali AyachitAbstract
Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can instead be distilled into the model's own representations during training, enabling hallucination detection from internal activations alone at inference time. We introduce a weak supervision framework that combines three complementary grounding signals: substring matching, sentence embedding similarity, and an LLM as a judge verdict to label generated responses as grounded or hallucinated without human annotation. Using this framework, we construct a 15000-sample dataset from SQuAD v2 (10500 train/development samples and a separate 5000-sample test set), where each example pairs a LLaMA-2-7B generated answer with its full per-layer hidden states and structured hallucination labels. We then train five probing classifiers: ProbeMLP (M0), LayerWiseMLP (M1), CrossLayerTransformer (M2), HierarchicalTransformer (M3), and CrossLayerAttentionTransformerV2 (M4), directly on these hidden states, treating external grounding signals as training-time supervision only. Our central hypothesis is that hallucination detection signals can be distilled into transformer representations, enabling internal detection without any external verification at inference time. Results support this hypothesis. Transformer-based probes achieve the strongest discrimination, with M2 performing best on 5-fold average AUC/F1, and M3 performing best on both single-fold validation and held-out test evaluation. We also benchmark inference efficiency: probe latency ranges from 0.15 to 5.62 ms (batched) and 1.55 to 6.66 ms (single sample), while end-to-end generation plus probe throughput remains approximately 0.231 queries per second, indicating negligible practical overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06277
PDF
-
Beyond Task-Driven Features for Object Detection
2026-04-04 19:34:13Meilun Zhou, Alina ZareAbstract
Task-driven features learned by modern object detectors optimize end task loss yet often capture shortcut correlations that fail to reflect underlying annotation structure. Such representations limit transfer, interpretability, and robustness when task definitions change or supervision becomes sparse. This paper introduces an annotation-guided feature augmentation framework that injects embeddings into an object detection backbone. The method constructs dense spatial feature grids from annotation-guided latent spaces and fuses them with feature pyramid representations to influence region proposal and detection heads. Experiments across wildlife and remote sensing datasets evaluate classification, localization, and data efficiency under multiple supervision regimes. Results show consistent improvements in object focus, reduced background sensitivity, and stronger generalization to unseen or weakly supervised tasks. The findings demonstrate that aligning features with annotation geometry yields more meaningful representations than purely task optimized features.
Abstract (translated)
URL
https://arxiv.org/abs/2604.03839
PDF
-
Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
2026-04-03 10:28:58Koshiro Nagano, Ryo Fujii, Ryo Hachiuma, Fumiaki Sato, Taiki Sekii, Hideo SaitoAbstract
Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby improving the robustness of model discrimination. However, many existing methods improve robustness only indirectly through the diversification of training samples and do not explicitly teach the model which regions in the input space truly contribute to discrimination; consequently, the model may learn spurious correlations caused by synthesis biases and artifacts. Motivated by this limitation, this paper proposes a learning framework that uses provenance information obtained during the training data synthesis process, indicating whether each region in the input space originates from the target object, as an auxiliary supervisory signal to promote the acquisition of representations focused on target regions. Specifically, input gradients are decomposed based on information about target and non-target regions during synthesis, and input gradient guidance is introduced to suppress gradients over non-target regions. This suppresses the model's reliance on non-target regions and directly promotes the learning of discriminative representations for target regions. Experiments demonstrate the effectiveness and generality of the proposed method across multiple tasks and modalities, including weakly supervised object localization, spatio-temporal action localization, and image classification.
Abstract (translated)
基于合成数据的学习方法因其能有效提升训练数据多样性、降低采集成本，进而增强模型判别鲁棒性而受到关注。然而，现有方法大多仅通过训练样本多样化间接提升鲁棒性，并未明确指导模型识别输入空间中真正贡献判别能力的区域；因此模型可能习得由合成偏差与伪影导致的虚假关联。针对这一局限，本文提出一种利用训练数据合成过程中获取的溯源信息作为辅助监督信号的学习框架，该信息指示输入空间中各区域是否源自目标对象，从而促进模型聚焦于目标区域的表征学习。具体而言，在合成过程中基于目标与非目标区域的信息对输入梯度进行分解，并引入输入梯度引导机制以抑制非目标区域的梯度响应。该方法可抑制模型对非目标区域的依赖，并直接促进目标区域判别性表征的学习。实验表明，所提方法在弱监督目标定位、时空动作定位及图像分类等多个任务与模态中均具有有效性与通用性。
URL
https://arxiv.org/abs/2604.02946
PDF
-
Rewrite the News: Tracing Editorial Reuse Across News Agencies
2026-03-31 16:10:26Soveatin Kuntur, Nina Smirnova, Anna Wroblewska, Philipp Mayr, Sebastijan Razbor\v{s}ek Ma\v{c}ekAbstract
This paper investigates sentence-level text reuse in multilingual journalism, analyzing where reused content occurs within articles. We present a weakly supervised method for detecting sentence-level cross-lingual reuse without requiring full translations, designed to support automated pre-selection to reduce information overload for journalists (Holyst et al., 2024). The study compares English-language articles from the Slovenian Press Agency (STA) with reports from 15 foreign agencies (FA) in seven languages, using publication timestamps to retain the earliest likely foreign source for each reused sentence. We analyze 1,037 STA and 237,551 FA articles from two time windows (October 7-November 2, 2023; February 1-28, 2025) and identify 1,087 aligned sentence pairs after filtering to the earliest sources. Reuse occurs in 52% of STA articles and 1.6% of FA articles and is predominantly non-literal, involving paraphrase and compositional reuse from multiple sources. Reused content tends to appear in the middle and end of English articles, while leads are more often original, indicating that simple lexical matching overlooks substantial editorial reuse. Compared with prior work focused on monolingual overlap, we (i) detect reuse across languages without requiring full translation, (ii) use publication timing to identify likely sources, and (iii) analyze where reused material is situated within articles. Dataset and code: this https URL.
Abstract (translated)
本文研究了多语言新闻中的句子级文本复用现象，分析了复用内容在文章中的分布位置。我们提出了一种无需完整翻译的弱监督跨语言句子级复用检测方法，旨在支持自动化预筛选以减轻记者信息过载负担（Holyst等，2024）。研究将斯洛文尼亚通讯社（STA）的英文文章与15家外国机构（FA）的七种语言报道进行对比，通过发布时间戳保留每句复用内容最早可能的外文来源。我们分析了两时间段（2023年10月7日-11月2日；2025年2月1日-28日）内1,037篇STA文章和237,551篇FA文章，经筛选最早来源后识别出1,087组对齐句子对。复用现象出现在52%的STA文章和1.6%的FA文章中，且主要为非字面复用，涉及意译及多源组合复用。复用内容倾向于出现在英文文章的中后部，而导语部分更常为原创内容，表明简单词汇匹配会忽略大量编辑层面的复用行为。相较于以往聚焦单语重叠的研究，本文（i）无需完整翻译即可检测跨语言复用，（ii）利用发布时间定位可能来源，（iii）分析复用材料在文章中的具体位置。数据集与代码：此https链接。
URL
https://arxiv.org/abs/2603.29937
PDF
-
ASI-Evolve: AI Accelerates AI
2026-03-31 12:04:17Weixian Xu, Tiantian Mi, Yixiu Liu, Yang Nan, Zhimeng Zhou, Lyumanshan Ye, Lin Zhang, Yu Qiao, Pengfei LiuAbstract
Can AI accelerate the development of AI itself? While recent agentic systems have shown strong performance on well-scoped tasks with rapid feedback, it remains unclear whether they can tackle the costly, long-horizon, and weakly supervised research loops that drive real AI progress. We present ASI-Evolve, an agentic framework for AI-for-AI research that closes this loop through a learn-design-experiment-analyze cycle. ASI-Evolve augments standard evolutionary agents with two key components: a cognition base that injects accumulated human priors into each round of exploration, and a dedicated analyzer that distills complex experimental outcomes into reusable insights for future iterations. To our knowledge, ASI-Evolve is the first unified framework to demonstrate AI-driven discovery across three central components of AI development: data, architectures, and learning algorithms. In neural architecture design, it discovered 105 SOTA linear attention architectures, with the best discovered model surpassing DeltaNet by +0.97 points, nearly 3x the gain of recent human-designed improvements. In pretraining data curation, the evolved pipeline improves average benchmark performance by +3.96 points, with gains exceeding 18 points on MMLU. In reinforcement learning algorithm design, discovered algorithms outperform GRPO by up to +12.5 points on AMC32, +11.67 points on AIME24, and +5.04 points on OlympiadBench. We further provide initial evidence that this AI-for-AI paradigm can transfer beyond the AI stack through experiments in mathematics and biomedicine. Together, these results suggest that ASI-Evolve represents a promising step toward enabling AI to accelerate AI across the foundational stages of development, offering early evidence for the feasibility of closed-loop AI research.
Abstract (translated)
人工智能能否加速其自身的发展？尽管近期的智能体系统在范围明确、反馈迅速的任务上展现出强劲性能，但它们能否应对那些驱动真正AI进步的高成本、长周期、弱监督的研究循环，仍不明确。我们提出了ASI-Evolve——一个面向AI研究的智能体框架，它通过“学习-设计-实验-分析”循环来闭合这一回路。ASI-Evolve通过两个关键组件增强了标准进化智能体：一是注入人类累积先验知识的认知库，用于每轮探索；二是将复杂实验结果提炼为可复用洞察的专用分析器，供后续迭代使用。据我们所知，ASI-Evolve是首个在AI发展的三大核心组件（数据、架构、学习算法）上均实现AI驱动发现的统一框架。在神经架构设计方面，它发现了105个最先进的线性注意力架构，其中最优模型超越DeltaNet达+0.97点，这一增益近乎近期人类设计改进的3倍。在预训练数据策划方面，进化管道将平均基准性能提升+3.96点，在MMLU（大学水平多学科理解测试）上的增益超过18点。在强化学习算法设计方面，发现的算法在AMC32、AIME24和OlympiadBench上分别超越GRPO达+12.5点、+11.67点和+5.04点。我们进一步通过数学与生物医学实验提供了初步证据，表明这种“AI for AI”范式能够超越AI技术栈进行迁移。综上，这些结果表明ASI-Evolve代表了一步有前景的探索，有望使AI在发展的基础阶段实现自我加速，并为闭环AI研究的可行性提供了早期证据。
URL
https://arxiv.org/abs/2603.29640
PDF
-
Industrial3D: A Terrestrial LiDAR Point Cloud Dataset and CrossParadigm Benchmark for Industrial Infrastructure
2026-03-30 16:46:40Chao Yin, Hongzhe Yue, Qing Han, Difeng Hu, Zhenyu Liang, Fangzhou Lin, Bing Sun, Boyu Wang, Mingkai Li, Wei Yao, Jack C. P. ChengAbstract
Automated semantic understanding of dense point clouds is a prerequisite for Scan-to-BIM pipelines, digital twin construction, and as-built verification--core tasks in the digital transformation of the construction industry. Yet for industrial mechanical, electrical, and plumbing (MEP) facilities, this challenge remains largely unsolved: TLS acquisitions of water treatment plants, chiller halls, and pumping stations exhibit extreme geometric ambiguity, severe occlusion, and extreme class imbalance that architectural benchmarks (e.g., S3DIS or ScanNet) cannot adequately represent. We present Industrial3D, a terrestrial LiDAR dataset comprising 612 million expertly labelled points at 6 mm resolution from 13 water treatment facilities. At 6.6x the scale of the closest comparable MEP dataset, Industrial3D provides the largest and most demanding testbed for industrial 3D scene understanding to date. We further establish the first industrial cross-paradigm benchmark, evaluating nine representative methods across fully supervised, weakly supervised, unsupervised, and foundation model settings under a unified benchmark protocol. The best supervised method achieves 55.74% mIoU, whereas zero-shot Point-SAM reaches only 15.79%--a 39.95 percentage-point gap that quantifies the unresolved domain-transfer challenge for industrial TLS data. Systematic analysis reveals that this gap originates from a dual crisis: statistical rarity (215:1 imbalance, 3.5x more severe than S3DIS) and geometric ambiguity (tail-class points share cylindrical primitives with head-class pipes) that frequency-based re-weighting alone cannot resolve. Industrial3D, along with benchmark code and pre-trained models, will be publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2603.28660
PDF
-
Hellinger Multimodal Variational Autoencoders
2026-03-30 14:53:45Huyen Vo, Isabel ValeraAbstract
Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture of experts (MoE), or their combinations to approximate the joint posterior. In this work, we revisit multimodal inference through the lens of probabilistic opinion pooling, an optimization-based approach. We start from Hölder pooling with $\alpha=0.5$, which corresponds to the unique symmetric member of the $\alpha\text{-divergence}$ family, and derive a moment-matching approximation, termed Hellinger. We then leverage such an approximation to propose HELVAE, a multimodal VAE that avoids sub-sampling, yielding an efficient yet effective model that: (i) learns more expressive latent representations as additional modalities are observed; and (ii) empirically achieves better trade-offs between generative coherence and quality, outperforming state-of-the-art multimodal VAE models.
Abstract (translated)
URL
https://arxiv.org/abs/2601.06572
PDF
-
OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
2026-03-29 11:43:02Qi Guo, Jue Wang, Yinhe Liu, Yanfei ZhongAbstract
Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change proposals using visual foundation models (VFMs) such as SAM and DINOv2, and then perform category identification with vision-language models (VLMs) such as CLIP. We reveal that category identification errors are the primary bottleneck of OVCD, mainly due to the limited ability of VLMs based on image-text matching to represent fine-grained land-cover categories. To address this, we propose OpenDPR, a training-free vision-centric diffusion-guided prototype retrieval framework. OpenDPR leverages diffusion models to construct diverse prototypes for target categories offline, and to perform similarity retrieval with change proposals in the visual space during inference. The secondary bottleneck lies in change localization, due to the inherent lack of change priors in VFMs. To bridge this gap, we design a spatial-to-change weakly supervised change detection module named S2C to adapt their strong spatial modeling capabilities for change localization. Integrating the pretrained S2C into OpenDPR leads to an optional weakly supervised variant named OpenDPR-W, which further improves OVCD with minimal supervision. Experimental results on four benchmark datasets demonstrate that the proposed methods achieve state-of-the-art performance under both supervision modes. Code is available at this https URL.
Abstract (translated)
开放词汇变化检测（OVCD）旨在通过超越预定义固定类别的泛化能力，识别任意感兴趣的变化。我们将OVCD重构为两阶段流程：首先利用SAM和DINOv2等视觉基础模型（VFMs）生成与类别无关的变化提案，随后通过CLIP等视觉-语言模型（VLMs）进行类别识别。研究发现，类别识别错误是OVCD的主要瓶颈，这主要源于基于图像-文本匹配的VLM在表征细粒度土地覆盖类别方面的能力有限。为此，我们提出OpenDPR——一个无需训练的、以视觉为中心的扩散引导原型检索框架。OpenDPR利用扩散模型离线构建目标类别的多样化原型，并在推理阶段在视觉空间与变化提案进行相似性检索。次要瓶颈在于变化定位，这源于VFMs本身缺乏变化先验知识。为弥合这一差距，我们设计了名为S2C的空间到变化弱监督变化检测模块，使其强大的空间建模能力适配变化定位任务。将预训练的S2C集成到OpenDPR中，形成了可选的弱监督变体OpenDPR-W，该变体通过最小监督进一步提升了OVCD性能。在四个基准数据集上的实验结果表明，所提方法在两种监督模式下均达到最先进性能。代码已公开于此链接。
URL
https://arxiv.org/abs/2603.27645
PDF
-
MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection
2026-03-25 02:51:26Yuang Geng, Junkai Zhou, Kang Yang, Pan He, Zhuoyang Zhou, Jose C. Principe, Joel Harley, Ivan RuchkinAbstract
In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are used directly for training and testing without any labels. This differs sharply from prior work that either requires extensive labeling (fully or weakly supervised) or depends on normal-only videos (one-class classification), which are vulnerable to distribution shifts and contamination. We propose an entropy-guided autoencoder that detects anomalies through reconstruction error by reconstructing normal frames well while making anomalies reconstruct poorly. The key idea is to combine the standard reconstruction loss with a novel Minimal Latent Entropy (MLE) loss in the autoencoder. Reconstruction loss alone maps normal and abnormal inputs to distinct latent clusters due to their inherent differences, but also risks reconstructing anomalies too well to detect. Therefore, MLE loss addresses this by minimizing the entropy of latent embeddings, encouraging them to concentrate around high-density regions. Since normal frames dominate the raw video, sparse anomalous embeddings are pulled into the normal cluster, so the decoder emphasizes normal patterns and produces poor reconstructions for anomalies. This dual-loss design produces a clear reconstruction gap that enables effective anomaly detection. Extensive experiments on two widely used benchmarks and a challenging self-collected driving dataset demonstrate that our method achieves robust and superior performance over baselines.
Abstract (translated)
本文针对单场景全无监督视频异常检测这一挑战性问题，即直接使用包含正常与异常事件的原始视频进行训练和测试而无需任何标签。这与以往需要大量标注（全监督或弱监督）或仅依赖正常视频（单类分类）的工作形成鲜明对比，后者易受分布偏移和污染影响。我们提出一种基于熵引导的自编码器，通过重建误差检测异常——使正常帧重建良好而异常帧重建较差。核心思想是在自编码器中结合标准重建损失与新颖的最小潜在熵（MLE）损失。仅靠重建损失虽能因正常与异常输入的固有差异将其映射到不同的潜在簇，但也可能过度优化异常重建而难以检测。因此，MLE损失通过最小化潜在嵌入的熵来解决此问题，促使嵌入向高密度区域集中。由于正常帧在原始视频中占主导，稀疏的异常嵌入会被拉入正常簇，从而使解码器聚焦正常模式并对异常产生较差重建。这种双损失设计形成了清晰的重建差距，可实现有效异常检测。在两个广泛使用的基准数据集及具有挑战性的自采驾驶数据集上的大量实验表明，我们的方法相比基线具有稳健且卓越的性能。
URL
https://arxiv.org/abs/2603.23868
PDF
-
FCL-COD: Weakly Supervised Camouflaged Object Detection with Frequency-aware and Contrastive Learning
2026-03-24 09:05:41Jingchen Ni, Quan Zhang, Dan Jiang, Keyu Lv, Ke Zhang, Chun YuanAbstract
Existing camouflage object detection (COD) methods typically rely on fully-supervised learning guided by mask annotations. However, obtaining mask annotations is time-consuming and labor-intensive. Compared to fully-supervised methods, existing weakly-supervised COD methods exhibit significantly poorer performance. Even for the Segment Anything Model (SAM), there are still challenges in handling weakly-supervised camouflage object detection (WSCOD), such as: a. non-camouflage target responses, b. local responses, c. extreme responses, and d. lack of refined boundary awareness, which leads to unsatisfactory results in camouflage scenes. To alleviate these issues, we propose a frequency-aware and contrastive learning-based WSCOD framework in this paper, named FCL-COD. To mitigate the problem of non-camouflaged object responses, we propose the Frequency-aware Low-rank Adaptation (FoRA) method, which incorporates frequency-aware camouflage scene knowledge into SAM. To overcome the challenges of local and extreme responses, we introduce a gradient-aware contrastive learning approach that effectively delineates precise foreground-background boundaries. Additionally, to address the lack of refined boundary perception, we present a multi-scale frequency-aware representation learning strategy that facilitates the modeling of more refined boundaries. We validate the effectiveness of our approach through extensive empirical experiments on three widely recognized COD benchmarks. The results confirm that our method surpasses both state-of-the-art weakly supervised and even fully supervised techniques.
Abstract (translated)
现有的伪装目标检测（COD）方法通常依赖于由掩码标注指导的全监督学习。然而，获取掩码标注耗时且劳动密集。与全监督方法相比，现有的弱监督COD方法性能显著较差。即便是Segment Anything Model（SAM），在处理弱监督伪装目标检测（WSCOD）时仍面临挑战，例如：a. 非伪装目标响应、b. 局部响应、c. 极端响应以及d. 缺乏精细化边界感知，导致在伪装场景中结果不理想。为缓解这些问题，本文提出一种基于频域感知与对比学习的WSCOD框架，命名为FCL-COD。为减轻非伪装对象响应问题，我们提出了频域感知低秩适应（FoRA）方法，将频域感知的伪装场景知识融入SAM。为克服局部与极端响应的挑战，我们引入了梯度感知对比学习方法，能有效勾勒精确的前景-背景边界。此外，为应对精细化边界感知缺失的问题，我们提出了多尺度频域表征学习策略，促进更精细化边界建模。我们在三个公认的COD基准数据集上通过大量实证实验验证了方法的有效性，结果证实我们的方法超越了最先进的弱监督乃至全监督技术。
URL
https://arxiv.org/abs/2603.22969
PDF
-
Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification
2026-03-23 02:50:52Jayanie Bogahawatte, Sachith Seneviratne, Saman HalgamugeAbstract
Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making few-shot weakly supervised WSI classification (FSWC) crucial for learning from limited slide-level labels. Recently, pre-trained vision-language models (VLMs) have been adopted in FSWC, yet they exhibit several limitations. Existing prompt tuning methods in FSWC substantially increase both the number of trainable parameters and inference overhead. Moreover, current methods discard instances with low alignment to text embeddings from VLMs, potentially leading to information loss. To address these challenges, we propose two key contributions. First, we introduce a new parameter efficient prompt tuning method by scaling and shifting features in text encoder, which significantly reduces the computational cost. Second, to leverage not only the pre-trained knowledge of VLMs, but also the inherent hierarchical structure of WSIs, we introduce a WSI representation learning approach with a soft hierarchical textual guidance strategy without utilizing hard instance filtering. Comprehensive evaluations on pathology datasets covering breast, lung, and ovarian cancer types demonstrate consistent improvements up-to 10.9%, 7.8%, and 13.8% respectively, over the state-of-the-art methods in FSWC. Our method reduces the number of trainable parameters by 18.1% on both breast and lung cancer datasets, and 5.8% on the ovarian cancer dataset, while also excelling at weakly-supervised tumor localization. Code at this https URL.
Abstract (translated)
全切片图像（WSIs）具有吉像素级规模，通常需在WSI分类流程中被分割为小实例以保障计算可行性。然而，获取大量实例级标注成本高昂，使得基于有限切片级标签学习的少样本弱监督WSI分类（FSWC）至关重要。近期，预训练视觉语言模型（VLMs）被应用于FSWC，但仍存在若干局限：现有FSWC中的提示调优方法显著增加了可训练参数量和推理开销；同时，当前方法会丢弃与VLM文本嵌入对齐度低的实例，可能导致信息损失。为应对这些挑战，我们提出两项关键贡献：第一，通过缩放和偏移文本编码器中的特征，提出一种新的参数高效提示调优方法，大幅降低计算成本；第二，为同时利用VLMs的预训练知识与WSIs的内在层次结构，我们引入一种不依赖硬实例过滤的软层次文本引导WSI表征学习方法。在涵盖乳腺癌、肺癌和卵巢癌类型的病理数据集上的综合评估表明，该方法在FSWC任务中相较于最新方法分别实现高达10.9%、7.8%和13.8%的持续提升。我们的方法在乳腺癌和肺癌数据集上减少18.1%的可训练参数，在卵巢癌数据集上减少5.8%，同时在弱监督肿瘤定位任务中表现卓越。代码见此链接。
URL
https://arxiv.org/abs/2603.21504
PDF
-
Harmful Visual Content Manipulation Matters in Misinformation Detection Under Multimedia Scenarios
2026-03-22 04:37:04Bing Wang, Ximing Li, Changchun Li, Jinjin Chi, Tianze Li, Renchu Guan, Shengsheng WangAbstract
Nowadays, the widespread dissemination of misinformation across numerous social media platforms has led to severe negative effects on society. To address this challenge, the automatic detection of misinformation, particularly under multimedia scenarios, has gained significant attention from both academic and industrial communities, leading to the emergence of a research task known as Multimodal Misinformation Detection (MMD). Typically, current MMD approaches focus on capturing the semantic relationships and inconsistency between various modalities but often overlook certain critical indicators within multimodal content. Recent research has shown that manipulated features within visual content in social media articles serve as valuable clues for MMD. Meanwhile, we argue that the potential intentions behind the manipulation, e.g., harmful and harmless, also matter in MMD. Therefore, in this study, we aim to identify such multimodal misinformation by capturing two types of features: manipulation features, which represent if visual content has been manipulated, and intention features, which assess the nature of these manipulations, distinguishing between harmful and harmless intentions. Unfortunately, the manipulation and intention labels that supervise these features to be discriminative are unknown. To address this, we introduce two weakly supervised indicators as substitutes by incorporating supplementary datasets focused on image manipulation detection and framing two different classification tasks as positive and unlabeled learning issues. With this framework, we introduce an innovative MMD approach, titled Harmful Visual Content Manipulation Matters in MMD (HAVC-M4 D). Comprehensive experiments conducted on four prevalent MMD datasets indicate that HAVC-M4 D significantly and consistently enhances the performance of existing MMD methods.
Abstract (translated)
如今，虚假信息在众多社交媒体平台上的广泛传播已对社会造成严重负面影响。为应对这一挑战，尤其在多媒体场景下对虚假信息的自动检测已备受学术界与工业界关注，并催生了名为多模态虚假信息检测（Multimodal Misinformation Detection, MMD）的研究任务。通常，当前MMD方法侧重于捕捉多模态间的语义关联与不一致性，却常忽略多模态内容中的某些关键指标。近期研究表明，社交媒体文章中视觉内容的篡改特征可作为MMD的重要线索。同时，我们认为篡改行为背后的潜在意图（如有害与无害）同样对MMD至关重要。因此，本研究旨在通过捕捉两类特征识别此类多模态虚假信息：一是表征视觉内容是否被篡改的篡改特征，二是评估篡改性质、区分有害与无害意图的意图特征。然而，监督这些特征具有判别性的篡改标签与意图标签均未知。为解决此问题，我们引入两种弱监督指标作为替代：通过整合专注于图像篡改检测的辅助数据集，并将两种不同分类任务构建为正与未标注学习问题。基于此框架，我们提出一种创新性MMD方法，命名为《MMD中有害视觉内容篡改至关重要》（Harmful Visual Content Manipulation Matters in MMD, HAVC-M4 D）。在四个主流MMD数据集上开展的全面实验表明，HAVC-M4 D能显著且稳定地提升现有MMD方法的性能。
URL
https://arxiv.org/abs/2603.21054
PDF
-
Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention
2026-03-21 09:28:05Jose Luis Lima de Jesus SilvaAbstract
Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert annotations are rarely available and subsurface information is intrinsically multimodal. The challenge is developing weakly supervised methods combining two-dimensional image texture with depth-aligned one-dimensional well-logs. Here, we introduce a weakly supervised multimodal segmentation framework that refines threshold-guided pseudo-labels through learned models. This preserves the annotation-free character of classical thresholding and clustering workflows while extending them with denoising, confidence-aware pseudo-supervision, and physically structured fusion. We establish that threshold-guided learned refinement provides the most robust improvement over raw thresholding, denoised thresholding, and latent clustering baselines. Multimodal performance depends strongly on fusion strategy: direct concatenation provides limited gains, whereas depth-aware cross-attention, gated fusion, and confidence-aware modulation substantially improve agreement with the weak supervisory reference. The strongest model, confidence-gated depth-aware cross-attention (CG-DCA), consistently outperforms threshold-based, image-only, and earlier multimodal baselines. Targeted ablations show its advantage depends specifically on confidence-aware fusion and structured local depth interaction rather than model complexity alone. Cross-well analyses confirm this performance is broadly stable. These results establish a practical, scalable framework for annotation-free segmentation, showing multimodal improvement is maximized when auxiliary logs are incorporated selectively and depth-aware.
Abstract (translated)
声波井孔图像可提供高分辨率的井壁结构信息，但大规模解释仍面临挑战，原因在于专家密集标注极为罕见且地下信息本质上是多模态的。本研究旨在开发一种弱监督方法，将二维图像纹理与深度对齐的一维测井曲线相结合。我们提出了一种弱监督多模态分割框架，通过模型学习来细化阈值引导的伪标签。该方法既保留了经典阈值法与聚类工作流无需标注的特性，又扩展了去噪、置信度感知伪监督及物理结构化融合功能。研究证实，基于阈值的模型学习细化相比原始阈值法、去噪阈值法及潜在聚类基线均能实现最稳健的性能提升。多模态性能高度依赖融合策略：直接拼接仅带来有限提升，而深度感知交叉注意力、门控融合及置信度感知调制则显著增强了与弱监督参考标准的一致性。最优模型置信度门控深度感知交叉注意力（CG-DCA）持续优于基于阈值、仅图像及早期多模态基线。针对性消融实验表明，其优势具体源于置信度感知融合与结构化局部深度交互，而非单纯模型复杂度。跨井分析进一步验证该性能具有广泛稳定性。这些成果确立了一种实用、可扩展的无标注分割框架，证明当辅助测井曲线被选择性地深度感知整合时，多模态改进效果达到最大化。
URL
https://arxiv.org/abs/2603.20729
PDF
-
Decoupled Sensitivity-Consistency Learning for Weakly Supervised Video Anomaly Detection
2026-03-20 09:15:37Hantao Zheng, Ning Han, Yawen Zeng, Hao ChenAbstract
Recent weakly supervised video anomaly detection methods have achieved significant advances by employing unified frameworks for joint optimization. However, this paradigm is limited by a fundamental sensitivity-stability trade-off, as the conflicting objectives for detecting transient and sustained anomalies lead to either fragmented predictions or over-smoothed responses. To address this limitation, we propose DeSC, a novel Decoupled Sensitivity-Consistency framework that trains two specialized streams using distinct optimization strategies. The temporal sensitivity stream adopts an aggressive optimization strategy to capture high-frequency abrupt changes, whereas the semantic consistency stream applies robust constraints to maintain long-term coherence and reduce noise. Their complementary strengths are fused through a collaborative inference mechanism that reduces individual biases and produces balanced predictions. Extensive experiments demonstrate that DeSC establishes new state-of-the-art performance by achieving 89.37% AUC on UCF-Crime (+1.29%) and 87.18% AP on XD-Violence (+2.22%). Code is available at this https URL.
Abstract (translated)
近期弱监督视频异常检测方法通过采用统一框架进行联合优化取得了显著进展。然而，该范式受限于根本性的敏感性-稳定性权衡问题：检测瞬态异常与持续异常的目标相互冲突，导致预测结果碎片化或响应过度平滑。为克服这一局限，我们提出DeSC——一种新颖的解耦敏感性-一致性框架，该框架采用不同的优化策略训练两个专用流。时序敏感性流采用激进优化策略以捕捉高频突变，而语义一致性流则施加稳健约束以维持长期连贯性并降低噪声。两个流通过协同推理机制融合其互补优势，该机制能减少个体偏差并产生均衡预测。大量实验表明，DeSC在UCF-Crime上达到89.37%的AUC（+1.29%），在XD-Violence上达到87.18%的AP（+2.22%），建立了新的最先进性能。代码已公开于此https链接。
URL
https://arxiv.org/abs/2603.19780
PDF
-
WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification
2026-03-19 10:57:44Isabel Rio-Torto, Jaime S. Cardoso, Lu\'is F. TeixeiraAbstract
Natural language explanations provide an inherently human-understandable way to explain black-box models, closely reflecting how radiologists convey their diagnoses in textual reports. Most works explicitly supervise the explanation generation process using datasets annotated with explanations. Thus, though plausible, the generated explanations are not faithful to the model's reasoning. In this work, we propose WeNLEX, a weakly supervised model for the generation of natural language explanations for multilabel chest X-ray classification. Faithfulness is ensured by matching images generated from their corresponding natural language explanations with original images, in the black-box model's feature space. Plausibility is maintained via distribution alignment with a small database of clinician-annotated explanations. We empirically demonstrate, through extensive validation on multiple metrics to assess faithfulness, simulatability, diversity, and plausibility, that WeNLEX is able to produce faithful and plausible explanations, using as little as 5 ground-truth explanations per diagnosis. Furthermore, WeNLEX can operate in both post-hoc and in-model settings. In the latter, i.e., when the multilabel classifier is trained together with the rest of the network, WeNLEX improves the classification AUC of the standalone classifier by 2.21%, thus showing that adding interpretability to the training process can actually increase the downstream task performance. Additionally, simply by changing the database, WeNLEX explanations are adaptable to any target audience, and we showcase this flexibility by training a layman version of WeNLEX, where explanations are simplified for non-medical users.
Abstract (translated)
URL
https://arxiv.org/abs/2603.18752
PDF
-
VirPro: Visual-referred Probabilistic Prompt Learning for Weakly-Supervised Monocular 3D Detection
2026-03-18 08:23:55Chupeng Liu, Jiyong Rao, Shangquan Sun, Runkai Zhao, Weidong CaiAbstract
Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision signals, providing complementary semantic context. However, hand-crafted textual descriptions struggle to capture the inherent visual diversity of individuals across scenes, limiting the model's ability to learn scene-aware representations. To address this challenge, we propose Visual-referred Probabilistic Prompt Learning (VirPro), an adaptive multi-modal pretraining paradigm that can be seamlessly integrated into diverse weakly supervised monocular 3D detection frameworks. Specifically, we generate a diverse set of learnable, instance-conditioned prompts across scenes and store them in an Adaptive Prompt Bank (APB). Subsequently, we introduce Multi-Gaussian Prompt Modeling (MGPM), which incorporates scene-based visual features into the corresponding textual embeddings, allowing the text prompts to express visual uncertainties. Then, from the fused vision-language embeddings, we decode a prompt-targeted Gaussian, from which we derive a unified object-level prompt embedding for each instance. RoI-level contrastive matching is employed to enforce modality alignment, bringing embeddings of co-occurring objects within the same scene closer in the latent space, thus enhancing semantic coherence. Extensive experiments on the KITTI benchmark demonstrate that integrating our pretraining paradigm consistently yields substantial performance gains, achieving up to a 4.8% average precision improvement than the baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17470
PDF
-
Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
2026-03-16 23:00:07Jaesung Bae, Xiuwen Zheng, Minje Kim, Chang D. Yoo, Mark Hasegawa-JohnsonAbstract
Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evaluation is costly and difficult to scale, and the scarcity of labeled data limits robust objective modeling. To address this, we propose a three-stage framework that leverages unlabeled dysarthric speech and large-scale typical speech datasets to scale training. A teacher model first generates pseudo-labels for unlabeled samples, followed by weakly supervised pretraining using a label-aware contrastive learning strategy that exposes the model to diverse speakers and acoustic conditions. The pretrained model is then fine-tuned for the downstream DSQA task. Experiments on five unseen datasets spanning multiple etiologies and languages demonstrate the robustness of our approach. Our Whisper-based baseline significantly outperforms SOTA DSQA predictors such as SpICE, and the full framework achieves an average SRCC of 0.761 across unseen test datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2603.15988
PDF
