MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts

• URL: http://arxiv.org/abs/2606.00844v1
• Date: Sat, 30 May 2026 18:34:30 GMT
• Title: MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts
• Abstract summary: MoEIoU is a mixture-of-experts based regression loss that models overlap, center alignment, and aspect-ratio mismatch.<n>It consistently outperforms standard and recent state-of-the-art losses, demonstrating faster convergence and improved localization accuracy.
• Score: 2.7501248535328315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bounding-box regression is a fundamental component of object detection, playing a critical role in precise object localization. Existing Intersection-over-Union (IoU)-based loss functions extend the IoU objective by incorporating geometric penalties, such as center-distance and aspect-ratio mismatch, to improve bounding-box regression. However, these penalties typically remain fixed throughout training and do not account for the optimization dynamics in which predicted boxes initially exhibit large center-distance and shape errors, with later stages focusing on improving overlap with the ground truth. To address this limitation, we introduce MoEIoU, a mixture-of-experts based regression loss that jointly models overlap, center alignment, and aspect-ratio mismatch. MoEIoU aggregates these components using a log-sum-exp function, which emphasizes the dominant localization error while maintaining smooth contributions from other terms. Additionally, a curriculum-based weighting schedule is employed to prioritize correcting box position and shape in early training stages and improving overlap in later stages. We evaluated proposed MoEIoU on PASCAL VOC, HRIPCB, and MS COCO using multiple YOLO architectures, along with large-scale simulation experiments. It consistently outperforms standard and recent state-of-the-art losses, demonstrating faster convergence and improved localization accuracy. We further show that this adaptive aggregation improves existing IoU-based losses, yielding consistent gains and providing more effective optimization guidance for bounding-box regression in object detection frameworks.

Related papers

• Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks [13.13897531291027]
  We propose a Fractional Semantic IoU loss to achieve unified semantic-geometric learning with gradient stabilization.<n>Our approach achieves stable performance gains across different bounding box formulations and diverse visual detection tasks.
  arXiv  Detail & Related papers  (2026-07-26T08:01:22Z)
• Efficient Adjoint Matching for Fine-tuning Diffusion Models [47.05085426361986]
  We propose EAM, which substantially improves training efficiency by reformulating the SOC problem with a textit base drift and a textitterminal cost.<n>EAM converges up to 4x faster than AM and matches or surpasses it across various metrics including PickScore, ImageReward, HPSv2.1, CLIPScore and Aesthetics.
  arXiv  Detail & Related papers  (2026-05-12T03:55:12Z)
• RELO: Reinforcement Learning to Localize for Visual Object Tracking [70.27265738642956]
  We introduce RELO, a REinforcement-learning-to-LOcalize method for visual object tracking.<n>RELO replaces handcrafted spatial priors with a localization policy learned over spatial positions.<n>We show that RELO achieves 57.5% AUC on LaSOText without template updates.
  arXiv  Detail & Related papers  (2026-05-08T07:34:29Z)
• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models [54.597200388738656]
  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples.<n>We show that many can be written under a common framework, which we call reward score matching (RSM)
  arXiv  Detail & Related papers  (2026-04-19T12:47:52Z)
• When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models [55.444604697848426]
  Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF.<n>The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which learns from pairwise data consisting of a pair of chosen and rejected responses.<n>We propose NormBT, an adaptive pair-wise normalization scheme that balances representation-driven effects and focuses learning signals on prediction error.
  arXiv  Detail & Related papers  (2025-12-06T08:15:37Z)
• WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training [64.0932926819307]
  We present Warmup-Stable and Merge (WSM), a framework that establishes a formal connection between learning rate decay and model merging.<n>WSM provides a unified theoretical foundation for emulating various decay strategies.<n>Our framework consistently outperforms the widely-adopted Warmup-Stable-Decay (WSD) approach across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-07-23T16:02:06Z)
• InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization [0.2529132677802514]
  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.<n>We show that our methods consistently outperform state-of-the-art IoU-based losses across various detection frameworks.
  arXiv  Detail & Related papers  (2025-07-16T17:09:04Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• A Plug-and-Play Learning-based IMU Bias Factor for Robust Visual-Inertial Odometry [27.62788405443008]
  We propose a novel plug-and-play module featuring the Inertial Prior Network (IPNet)<n>IPNet infers an IMU bias prior by implicitly capturing the motion characteristics of specific platforms.<n>In this work, we first directly infer the biases prior only using the raw IMU data using a sliding window approach.
  arXiv  Detail & Related papers  (2025-03-16T14:45:19Z)
• Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
  This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem. PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
  arXiv  Detail & Related papers  (2024-04-01T07:49:11Z)
• SIoU Loss: More Powerful Learning for Bounding Box Regression [0.0]
  Loss function SIoU was suggested, where penalty metrics were redefined considering the angle of the vector between the desired regression. Applied to conventional Neural Networks and datasets it is shown that SIoU improves both the speed of training and the accuracy of the inference.
  arXiv  Detail & Related papers  (2022-05-25T12:46:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.