CNN
-
Polarization Aware Deep Learning Framework for SAR Despeckling
2026-11-10 10:25:36Gianpaolo Passarello, Sergio Vitale, Hossein Aghababei, Giampaolo Ferraioli, Vito PascazioAbstract
Speckle is an inherent characteristic of synthetic aperture radar (SAR) imagery that complicates image interpretation and the extraction of reliable information. Although deep-learning-based despeckling methods have demonstrated promising performance, their applicability across different polarimetric configurations is often limited by the need for specialized architectures or separate training procedures. This paper presents a unified deep-learning framework for despeckling single-, dual-, and full-polarization SAR data using a single trained convolutional neural network. The proposed approach adopts a common nine-channel representation of the polarimetric covariance matrix and a polarization-aware masking strategy to accommodate different configurations without modifying the network architecture. Qualitative and quantitative comparison on three different scenes from different sensors demonstrate competitive performance across the considered experiments and support the feasibility of a unified, polarization-flexible approach to SAR despeckling across different polarimetric configurations.
Abstract (translated)
URL
https://arxiv.org/abs/2611.10091
PDF
-
picoEmergencyNet : Attention-Enhanced Ultra-Small Deep Learning Model for Aerial Image Classification in Emergency Monitoring
2026-11-10 06:28:44Christos KyrkouAbstract
Real-time disaster recognition from aerial imagery requires deep learning models that operate under strict memory, compute, and latency constraints. While recent approaches achieve high accuracy, their computational cost limits deployment on resource-constrained UAV platforms. This work introduces picoEmergencyNet, an ultra-lightweight convolutional neural network designed for aerial image disaster classification. The proposed architecture combines depthwise dilated convolutions with efficient channel attention and channel shuffling to enable multi-scale feature extraction at minimal computational cost. picoEmergencyNet has 23k parameters and 7M FLOPs, requiring only 0.1 MB of model storage. Evaluated on the AIDER and AIDERv2 disaster datasets, it achieves up to 96.1% accuracy, matching or exceeding state-of-the-art lightweight models that are orders of magnitude larger. Deployment experiments on the NVIDIA Jetson AGX Orin show that, without hardware-specific optimizations, picoEmergencyNet achieves 258 FPS on GPU and 46 FPS on CPU with a 7x lower activation memory footprint compared to competing models. These results demonstrate that careful architectural specialization, rather than model scaling, enables highly efficient and accurate TinyML-ready disaster recognition for real-time UAV-based emergency monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13638
PDF
-
Spectral-Convolutional Factorized Transformer for Joint Multipath Parameter Estimation: Applications to mmWave Positioning and Radio SLAM
2026-11-10 05:28:19Yaya Etiabi, Wessam Ajib, Halima ElbiazeAbstract
Future 6G wireless networks are expected to evolve toward AI-native systems that support intelligent, environment-aware services, including positioning and mapping. Current research has already integrated AI into several aspects of communication, particularly wireless channel estimation. However, most learning-based channel estimators focus on communication-oriented objectives rather than explicitly estimating multipath parameters such as delay, angle of arrival (AoA), and angle of departure (AoD). These parameters provide essential geometric information for downstream tasks including positioning and radio simultaneous localization and mapping (SLAM). In this work, we propose a Spectral-Convolutional Factorized Transformer (SCFT) for joint multipath component (MPC) estimation from noisy complex channel estimates and physical beam-pair descriptors. SCFT combines local spectral convolution, permutation-equivariant beam-set attention, and a query-based Transformer decoder to detect and classify line-of-sight and non-line-of-sight paths and estimate their observed delays, AoAs, and AoDs. Experiments on realistic ray-tracing data show that SCFT reduces the generalized optimal sub-pattern assignment error by 13.1% compared with ResNet, the strongest competing baseline. We further demonstrate this advantage in independent snapshot positioning and radio SLAM, where SCFT reduces position RMSE by 18.5% and 65.0%, respectively, relative to ResNet. These findings highlight the importance of explicitly recovering multipath geometry, as improvements in MPC estimation can translate into substantial gains in downstream tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.01491
PDF
-
Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification
2026-11-09 22:22:04M. Bolhassani, W. Furtado, D. Duvall, MJ Negahdar, J. Joshi, S. Contractor, A. AminiAbstract
We studied domain shift in adult elbow fracture classification from radiographs when training on a large public dataset and deploying on a small, institution-specific dataset (UofL). We implemented a domain-adversarial neural network (DANN) to align feature distributions across source (MURA) and target (UofL) domains while optimizing fracture classification. A pretrained convolutional backbone was adapted to grayscale inputs; the task head predicts fracture presence, and a gradient-reversal-based domain head encourages domain-invariant features via adversarial learning. We compared four settings: (1) Source-only, (2) Target-only (limited labels), (3) Naive merge (pooled training), and (4) DANN (MURA to UofL). Evaluation on UofL test data uses AUC-ROC, and accuracy. DANN outperformed Source-only and Naive merge baselines by reducing domain bias without overfitting to the small target set. Ablations showed that progressive adversarial weight, dataset-size-aware domain loss, and domain-balanced sampling improved stability and target performance. Results demonstrated that domain alignment is a practical path to robust clinical generalization from public to local data.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13308
PDF
-
Rethinking Evaluation for Video Capsule Endoscopy: Validation Protocol, Source-Video Diversity, and Cross-Dataset Shift
2026-11-09 21:20:54Smriti Regmi, Debesh JhaAbstract
Automated video capsule endoscopy (VCE) classification remains challenging due to severe class imbalance, limited source-video diversity, and variations in image appearance across datasets. Although deep learning models have demonstrated promising performance on established benchmarks, their reliability under different validation protocols and external dataset shift remains insufficiently understood. In this work, we introduce DMSNet, a deformable adaptive multi-scale edge-guided attention network integrating adaptive multi-scale feature fusion, deformable lesion refinement, edge-guided attention, and sparse feature selection. We benchmark DMSNet against 18 representative convolutional, transformer-based, and pretrained vision architectures on Kvasir-Capsule under random frame-level and source-video-disjoint validation protocols. We further identify source-video overlap between the original training and test splits and evaluate model performance on both the complete test set and a source-video-disjoint subset. Under random frame-level validation, DMSNet achieves an MCC of 0.442 $\pm$ 0.020 on complete test set and 0.456 $\pm$ 0.037 on the source-video-disjoint subset. On the external CV2024 dataset, ConvNeXt-Tiny achieves the highest MCC of 0.207, while performance degrades substantially across architectures relative to in-domain evaluation. We further investigate source-video diversity using a per-class cap of 200 training frames. With the total training-set size held fixed, increasing the maximum source-video coverage from four to eight improves MCC for 17 of 19 evaluated architectures. Overall, these findings demonstrate that model rankings and classification performance depend substantially on evaluation protocol, training-source diversity, and cross-dataset shift, emphasizing the need for source-aware validation and rigorous external evaluation of VCE classification systems.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13245
PDF
-
Just Image Transformers with Late-Stage Pixel Refinement
2026-11-09 19:08:13Denis Lukovnikov, Andreas M\"uller, Asja FischerAbstract
Recent work on latent-free diffusion transformers has demonstrated the feasibility of training image generators without a latent VAE. This avoids compression artifacts from the VAE and simplifies the training pipeline. In particular, JiT showed that even a standard transformer can be trained to generate images when the model is trained to predict the final image ($x$-prediction). Even though JiT unlocks training efficiency comparable to latent models, it still suffers from reduced image quality likely arising from modeling the image as a collection of large patches. In this work, we revisit JiT and show that adding simple convolutional pixel-pathway layers in a post-training phase significantly improves generation quality. Moreover, we show that the added pixel-pathway does not need to be active in the early denoising stages, and can be activated as late as in the last $20\%$ of the denoising process. Our experiments on ImageNet@256 show improvements compared to the original JiT results, achieving an FID of $1.78$ (from $2.34$ with corrected sampling), without using additional losses.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13120
PDF
-
Is a CNN-Transformer Ensemble Worth It When a Chest X-Ray Foundation Model Is Available?
Abstract
Ensembles of ImageNet-pretrained convolutional networks and Vision Transformers are a common way to improve multi-label chest X-ray classification. We ask whether such an ensemble is still worth its cost when a model pretrained on chest radiographs is available. On the official patient-disjoint split of NIH ChestX-ray14 (25,596 test images, 2,797 patients), we train five ImageNet-pretrained backbones and the EVA-X-S foundation model with validation-only model selection, compare five fusion rules, and estimate every difference with a patient-level paired bootstrap. EVA-X-S alone reached a test macro-AUROC of 0.828; the five-model ensemble reached 0.814 (difference -0.0136, 95% CI -0.0178 to -0.0098) at about 7.8 times the summed backbone latency and ten times the parameters. Averaging the five ImageNet models with EVA-X-S changed AUROC by -0.0056 (-0.0095 to -0.0021). With all five ImageNet backbones trained with the EVA-X-S recipe, their ensemble scored 0.817, still -0.0109 (-0.0142 to -0.0076) below EVA-X-S, and across three seeds EVA-X-S varied by at most 0.001 AUROC. Under the ImageNet models' recipe, however, EVA-X-S fell to 0.798. Our full-stacking configuration never outperformed calibrated averaging. In this setting, the tested ImageNet ensembles did not improve on a single chest X-ray foundation model fine-tuned with its own recipe.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13014
PDF
-
khammoon: From a Linguistic Guideline to a Thai Morpheme Segmenter
2026-11-09 03:19:53Warit Sirichotedumrong, Adisai Na-Thalang, Chanakan Wittayasakpan, Kritsadha Phatcharoen, Kunat PipatanakulAbstract
Thai is written without spaces between words, making segmentation a foundational step in most Thai NLP pipelines. Existing tools primarily reproduce the word-level conventions of corpora such as BEST; however, because the notion of a "word" in Thai lacks a unified linguistic consensus, these conventions struggle with productive compounding, leading to arbitrary boundaries and ambiguity in downstream representations. Instead, we propose operating at the morphological level, focusing on khammoon, the smallest atomic unit that carries meaning. Segmenting at the morphemic level provides an explicit, consistent morphological representation that eliminates compounding ambiguity. Crucially, this representation benefits downstream learning: models trained on morphemes perform on par with or exceed word-level baselines across part-of-speech tagging, named-entity recognition, and sentiment classification, demonstrating that linguistic consistency improves representation quality without downstream performance penalty. To operationalize this representation, we translate linguistic principles into a formal decision guideline with near-perfect human agreement ($\kappa \approx 0.99$), scale annotation with an LLM, and correct systematic errors with human labels. Finally, we train khammoon, a lightweight 1M-parameter convolutional BiLSTM segmenter designed for efficient CPU inference, achieving a boundary F1 of 0.992 on out-of-domain text. The guideline, datasets, model, and library are all publicly released.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13012
PDF
-
ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations
2026-11-06 18:55:34Aaron Sun, Yachan Liu, Ping Yang, Peng Bai, Subhransu MajiAbstract
Zeolites are an important class of porous crystalline materials with broad applications in gas storage, separations, and catalysis. Although hundreds of thousands of experimentally realized and hypothetical zeolite structures are known, identifying materials optimized for a target application remains challenging because property labels are expensive to obtain and available only for limited structure-molecule pairs. While prior work has demonstrated that 3D neural representations can predict zeolite properties effectively, it remains unclear which representation-learning strategies are most effective in the low-data regime relevant to materials discovery. We present ZeoBench, a benchmark for self-supervised learning on dense 3D representations of all-silica zeolites, and evaluate the resulting features on six existing downstream adsorption-property prediction tasks, across a range of training set sizes. Our study compares self-supervised 3D pretraining on volumetric zeolite data, adaptations of image-pretrained 2D ConvNets and vision transformers to 3D via multiview and channel-inflation strategies, and 3D ConvNets pretrained on out-of-domain volumetric datasets, alongside hand-crafted descriptors and supervised baselines. Using our pretraining and evaluation framework, we find self-supervised 3D representations outperform existing methods and achieve state-of-the-art performance across both in-domain label regimes and for the unseen domain of metal organic frameworks. Learned representations consistently outperform hand-crafted descriptors, and convolutional architectures are generally more effective than vision transformers in this setting. These results establish ZeoBench as a practical benchmark for 3D representation learning in zeolites and provide guidance for data-limited adsorption property prediction.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09880
PDF
-
Graded convolutional networks: scale invariance without the scale and robustness to unknown blur
Abstract
The Gaussian jet of an image is a graded vector space: a dilation by $\lambda$ multiplies derivatives of order $k$ by $\lambda^{-k}$. Local graded convolutions are exactly homogeneous differential operators, and a local feature is dilation-invariant if and only if it factors through the scale-normalized jet or, without the scale, through the retraction onto the weighted sphere of the grading. Under unknown Gaussian blur the retraction changes only by a change of scale, whereas the scale-normalized jet acquires a grading factor that no radial normalization removes. At the zero jet the retraction separates image families that radial normalizations and continuous classifiers cannot. Networks built on the retraction are universal for invariant features. On MNIST such a network keeps 88.4% accuracy under a two-pixel blur, against 66.2% for the same network on scale-normalized derivatives; in Lindeberg's Gaussian derivative network the retraction raises accuracy at that blur from 91.5% to 95.1%.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09878
PDF
-
A lightweight convolutional neural network for target detection in an edge environment
2026-11-06 17:22:37Hughes Perreault, Ola Ahmad, Daniel CzubokaAbstract
This paper proposes a novel, lightweight convolutional neural network (CNN) designed for edge device deployment. The CNN is developed to recognize and classify threats or targets of interest. The model is equipped with a real-time hotspot detection algorithm, which enables it to process information quickly and accurately, resulting in improved inference time of up to 20 fps and a detection range of more than 400 meters with typical thermal situational awareness sensors. The proposed CNN has been rigorously tested and validated to demonstrate its high accuracy, sensitivity, and low false positive rate, providing a reliable solution for edge devices to detect potential targets. Additionally, the lightweight design of the CNN allows for easy deployment, making it an ideal solution for extending the security bubble for edge devices. The proposed model can be used for a variety of applications, including surveillance, security, and object recognition.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09756
PDF
-
Evaluating Anterior Cruciate Ligament Risk of Injury Using a Graph Convolutional Autoencoder
2026-11-06 17:00:42Athanasios Babouras, Paul A. Martineau, Thomas FevensAbstract
Current solutions for assessing the risk of anterior cruciate ligament (ACL) injury typically rely on expensive motion-capture labs that require substantial resource investment or subjective evaluations of specific athletic stress tests by experts. The Drop Vertical Jump (DVJ) and the Single Leg Hop (SLH) are two examples of such tests typically used to track progress in ACL rehabilitation. In this paper, we develop an unsupervised learning model that runs entirely on a smartphone for two tasks, based on an autoencoder architecture with multiple layers of graph convolutional networks, which utilizes pose estimation data to determine a person's injury risk status. Our model accurately predicts athletes at high risk of injury for both athletic stress tests, with average sensitivities and specificities of 78% and 78% for the DVJ, and 75% and 74% for the SLH. Our findings support the development of a widely accessible smartphone solution for real-time screening of ACL injury risk.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09724
PDF
-
SURE:Spatiotemporal Uncertainty Representation for Efficient Vision-Language-Action Learning
2026-11-06 16:32:49Jingye Zhang, Choo Sin Wai, Dake Zhong, Zhifang Liu, Yuhong Zhang, Siyao Xiao, Guorui Song, Guocun Wang, Dongbin Zhang, Peng Jiao, Haoqian WangAbstract
Vision-language-action (VLA) policies have become a promising paradigm for end-to-end robot control, but their effectiveness still depends heavily on large volumes of demonstration data. In manipulation tasks, this dependence is compounded by structured spatiotemporal uncertainty in the action space: multiple nearby actions or trajectories may successfully solve the same task, while semantically equivalent demonstrations often unfold at different speeds. Standard pointwise supervision treats each demonstrated action as an exact target, imposing an unnecessary learning burden under such uncertainty. We present SURE, a data-efficient VLA training framework that explicitly models both spatial and temporal uncertainty. SURE augments a VLA backbone with a lightweight transposed-convolutional probabilistic action decoder that captures spatial uncertainty through local correlations among neighboring action bins. It further introduces Soft-DTW alignment supervision to accommodate local timing variations between predicted and demonstrated action chunks. Together, these two components reduce sensitivity to demonstrator-specific poses and execution timing, enabling more data-efficient action learning. We evaluate SURE on LIBERO, RoboTwin 2.0, and real-world manipulation tasks. Even with only 10% of the demonstration data or 20% of the training steps, SURE achieves manipulation success rates that match or surpass baseline VLAs.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09684
PDF
-
Dual Architecture Fusion Vehicle Lidar 3D Target Detection
2026-11-06 16:13:58Muyun Li, Weizheng Jin, Yuan SunAbstract
In this paper, a 3D backbone network (SpconvTransformer) based on the fusion of convolutional architecture branch and Transformer architecture branch is proposed. The convolution branch uses 3D sparse convolution and submanifold convolution to learn local voxel features and semantic information, and the Transformer branch uses the self-attention mechanism to model the remote relationship between voxels, uses the broad receptive field to capture rich context information, and complementing the advantages of the two architectures by fusing the local features extracted from the two branches and the global features solves the problem of limited receptive fields of 3D convolutional neural networks. The experimental results show that the average accuracy of SpconvTransformer in 3D object detection and bird's-eye view detection tasks reaches 81.45% and 88.09%, respectively, and the average directional similarity reaches 91.10%, which is significantly better than other existing algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09664
PDF
-
NAVE: A Normalized, Adaptive Conformer for Antarctic Whale Vocalization Detection
2026-11-06 15:54:21Matthias Nagl, Paul Primus, Gerhard WidmerAbstract
Antarctic whale vocalization detection requires temporally localizing call boundaries in long underwater recordings and classifying them into predefined call types. Training reliable machine learning models for this task is difficult due to the variability and sparsity of whale calls in passive acoustic monitoring datasets. These difficulties are further amplified by time-varying noise that can mask whale calls and by site-specific ambient sound characteristics to which a trained model may not generalize. In this work, we present NAVE, a Conformer-based detector that improves whale-call detection via three components. First, its input representation combines per-bin complex mean subtraction, which suppresses constant site-specific ambient sound characteristics, with an additional per-channel energy normalization (PCEN) channel that adapts to temporal variations in the noise floor. Second, a frequency-dynamic stem processes these noise-aware representations with convolutions that adapt across the characteristic frequency bands of the target call types. Third, we use a Conformer backbone with a convolution kernel matched to the duration of the target calls that adds an inductive bias and improves temporal localization. We evaluate NAVE on BioDCASE 2026 Task 2 using leave-one-site-out cross-validation across the validation sites, which approximates deployment on unseen recording sites. A single NAVE model with a tuned per-class threshold exceeds the stronger WhaleVAD-BPN baseline, using no boundary-proposal network and no search over post-processing parameters. A controlled ablation study shows that the normalized front-end and a duration-matched convolutional kernel each contribute substantially to recovering the D downsweep, the hardest class for previous detectors, with the wide kernel giving the largest aggregate gain.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09642
PDF
-
MoRE-GS: Motion-Regime Experts for Future Gaussian Splatting
Abstract
Future dynamic novel-view synthesis requires extrapolating multiple motion regimes within the same scene. A single dynamics model may not simultaneously represent stationary regions, coordinated motion, local interactions, and articulated trajectories. We introduce Motion Regime Expert Routing for Gaussian Splatting (MoRE-GS), a causal, render-aware framework for forecasting dynamic 3D Gaussian scenes. MoRE-GS freezes a Gaussian representation reconstructed exclusively from the observed temporal prefix and forecasts its control-keypoint motion using four complementary experts: persistence, a coefficient-space Transformer, a graph convolutional network, and a structured Transformer with rigid and non-rigid motion constraints. A compact routing table assigns expert mixtures across soft motion groups and forecast-horizon bins, while a persistence gate suppresses unreliable extrapolation. Across D-NeRF and HyperNeRF scenes, MoRE-GS achieves improved performance against other methods, and these results demonstrate that renderer-calibrated composition of complementary motion predictors improves causal dynamic Gaussian forecasting across heterogeneous motion regimes. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.00375
PDF
-
The Role Of Recurrent Refinement In Medical Image Segmentation
2026-11-06 13:08:41Joao D. S. Marques, David Calhas, Arlindo L. OliveiraAbstract
While feed-forward segmentation networks perform well on large cohorts, they degrade in constrained clinical settings with few training samples and imaging artifacts. Human vision, by contrast, remains robust under these conditions, a property partly attributed to the recurrent and feedback connectivity of the visual cortex, which refines visual information over time. Inspired by this, we append lightweight recurrent refinement blocks to segmentation backbones, namely Conditional Random Fields (CRFs), modern Hopfield networks and convolutional GRUs, and study their behaviour as the number of iterations increases at test time (including beyond the training horizon). Evaluated on two open-source datasets, Kvasir- SEG and ARCADE, our recurrent blocks add less than 1.5% parameters and yield gains on clean data (up to 1.4 pp) and under noise (up to 17 pp) while reducing HD95. Code is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2611.09436
PDF
-
Concordance-Optimal Continuous Music Emotion Estimation: Variance Decomposition, Dual-Branch Temporal Fusion, and Conformal Prediction Intervals
2026-11-06 04:23:46Mohammad Faraz Akhtar, Aditya Parashar, Ayush Jain, Madhur Gupta, Ritesh Kumar, Soubhik ChakrabortyAbstract
Continuous music emotion recognition (MER) estimates how Arousal and Valence evolve within a song, yet the field's standard metric, pooled frame-level correlation, is dominated by between-song differences and cannot distinguish a model that tracks emotional dynamics from one that only ranks songs by their average level. We decompose annotation variance into between- and within-song components and show that mean squared error (MSE) targets the former, while windowed Lin's concordance correlation coefficient (CCC = $r \cdot C_b$) targets the latter by penalising the variance compression MSE induces. A single weight $\lambda$ controls the trade-off: on 1,764 DEAM songs, raising $\lambda$ from 0 to 1 lowers pooled Arousal $r$ from 0.843 to 0.810 while raising mean within-song $r$ from 0.204 to 0.368. Building on this objective, we present MMAS (Multimodal Music Analysis System), an open-source model that predicts Arousal and Valence every 0.5 s from raw audio. It fuses frozen MERT-v1-95M embeddings with ten symbolic features from automatic transcription through a dual-branch temporal convolutional network with cross-modal attention. Because both branches are audio-derived, one model trains jointly on DEAM and PMEmo without domain conditioning. Under song-grouped 5-fold cross-validation (2,531 songs), pooled $r$ reaches 0.801/0.685 (Arousal/Valence) on DEAM and 0.742/0.746 on PMEmo. Against a ridge baseline on identical features, within-song Arousal $r$ roughly triples (0.344 vs. 0.125; $n = 353$ songs, Wilcoxon $p = 1.7 \times 10^{-21}$, $d = 0.56$). Complete transcription failure costs at most 0.04 pooled $r$. Split-conformal intervals attain 93.7% (Arousal) and 90.0% (Valence) marginal coverage at a 95% target, with the shortfall traced to within-song dependence. MMAS is released as a pip-installable package.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08966
PDF
-
DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence
2026-11-06 03:46:19Kiljoon Han, Kyumin Hwang, Wonhyeok Choi, Jeonghoon Kim, Sunghoom ImAbstract
Iterative refinement models have significantly improved stereo matching accuracy, but their rigid, fixed update schedules incur heavy computational costs and a strict trade-off between speed and accuracy. This challenge is magnified in video streams, where traditional online methods resort to reducing feature channels or relying on expensive temporal warping. To address this, we propose DEQ-Stereo, a novel video stereo matching framework based on the Deep Equilibrium (DEQ) paradigm. Instead of unrolling a fixed number of iterations, DEQ-Stereo reformulates the refinement as an implicit fixed-point problem, adaptively terminating once convergence is met. To ensure fast and stable intra-frame convergence, we introduce the Convolutional Simplified Gated Unit (ConvSGU), which eliminates unnecessary non-linearities by modeling the latent state as a gated, element-wise sum of inputs. Furthermore, to exploit cross-frame temporal coherence, we propose Temporal State Transfer (TST), a warm-start strategy that propagates the converged hidden state to the next frame without requiring explicit pose or warping priors. Extensive evaluations demonstrate that DEQ-Stereo delivers state-of-the-art performance with a superior accuracy-to-latency trade-off.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39701
PDF
-
Impact of color in computer and human-based object recognition under occlusion
2026-11-06 00:01:47Courtney M. King, Elissa Aminoff, Daniel D. LeedsAbstract
Partial occlusions challenge object recognition in both human and computer vision (CV), but the impact is largely dependent on the occlusion and model design. Properties relating to color are particularly important in biological recognition and frequently leveraged for camouflage, however there are still open questions about what makes them effective and how they translate to CV. This work studies partial occlusions that create camouflage, including those that blend in with target objects or with scenes, which alter object representations in distinct ways. Experiments evaluate recognition performance on both human participants and models ranging from convolutional neural networks (CNNs) to transformers, and additional analysis is performed on models to uncover trends in processing and object representations under multiple occlusion types. Novel metrics offer explainability of model behavior under occlusion: non-occlusion precision (NOP) and non-occlusion recall (NOR) measure alignment of model activations with and without occlusion, and activation in occlusion (AIO) measures the percentage of activations that occur in occluded regions. Findings show that human recognition, and most transformers, are negatively impacted by generated camouflaging occluders, with scene-based camouflage performing worse than object-based. Classical CNNs show a strong opposite trend, performing the worst on neutral-colored occlusions, suggesting that contextually-related colors, particularly scene-based, benefit object recognition rather than disrupting shape or boundary cues. Additionally, generated camouflaging occluders for training augmentation improves robustness to unseen camouflage for selected CNN model, and occlusion metrics suggest trends about learned mechanisms. Findings have interesting implications for alignment in human and computer vision, model vulnerabilities, and explainability.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08808
PDF
