Paper Reading AI Learner

InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization

2025-07-16 17:09:04
Haoyuan Liu, Hiroshi Watanabe

Abstract

Bounding box regression (BBR) is fundamental to object detection, where the regression loss is crucial for accurate localization. Existing IoU-based losses often incorporate handcrafted geometric penalties to address IoU's non-differentiability in non-overlapping cases and enhance BBR performance. However, these penalties are sensitive to box shape, size, and distribution, often leading to suboptimal optimization for small objects and undesired behaviors such as bounding box enlargement due to misalignment with the IoU objective. To address these limitations, we propose InterpIoU, a novel loss function that replaces handcrafted geometric penalties with a term based on the IoU between interpolated boxes and the target. By using interpolated boxes to bridge the gap between predictions and ground truth, InterpIoU provides meaningful gradients in non-overlapping cases and inherently avoids the box enlargement issue caused by misaligned penalties. Simulation results further show that IoU itself serves as an ideal regression target, while existing geometric penalties are both unnecessary and suboptimal. Building on InterpIoU, we introduce Dynamic InterpIoU, which dynamically adjusts interpolation coefficients based on IoU values, enhancing adaptability to scenarios with diverse object distributions. Experiments on COCO, VisDrone, and PASCAL VOC show that our methods consistently outperform state-of-the-art IoU-based losses across various detection frameworks, with particularly notable improvements in small object detection, confirming their effectiveness.

Abstract (translated)

边界框回归(BBR)在目标检测中至关重要,其中回归损失对于精确定位极为关键。现有的基于IoU的损失通常会采用手工设计的几何惩罚项来解决非重叠情况下的IoU不可微问题,并提高BBR性能。然而,这些惩罚项对边界框形状、大小和分布非常敏感,常常导致小目标优化不佳以及由于与IoU目标不一致而导致的边界框扩大的不良行为。 为了解决这些问题,我们提出了InterpIoU,这是一种新的损失函数,它用基于插值边界框与目标之间IoU的新项来替代手工设计的几何惩罚项。通过使用插值边界框作为预测和真实值之间的桥梁,InterpIoU能够在非重叠情况下提供有意义的梯度,并且从根本上避免了由于不匹配的惩罚而导致的边界框扩大的问题。仿真结果进一步表明,IoU本身就是一个理想的回归目标,现有的几何惩罚不仅没有必要,而且效果不佳。 基于InterpIoU,我们还引入了动态插值IoU(Dynamic InterpIoU),该方法能够根据IoU值动态调整插值系数,从而提高对具有不同对象分布场景的适应能力。在COCO、VisDrone和PASCAL VOC上的实验显示,我们的方法在各种检测框架中始终优于现有的基于IoU的损失函数,并且特别是在小目标检测方面取得了显著改进,证实了其有效性。

URL

https://arxiv.org/abs/2507.12420

PDF

https://arxiv.org/pdf/2507.12420.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot