Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks

• URL: http://arxiv.org/abs/2607.23530v1
• Date: Sun, 26 Jul 2026 08:01:22 GMT
• Title: Geometry Meets Semantics: Fractional Gradient Stabilization for Semantic-Driven Bounding Box Optimization in Visual Detection Tasks
• Abstract summary: 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.
• Score: 13.13897531291027
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Bounding boxes are fundamental for object localization in visual detection tasks. Among them, oriented bounding boxes are widely used in visual detection tasks, which provide a more precise directional representation. Generally, IoU-based losses are widely adopted to optimize box regression. However, we observed that IoU-driven box optimization suffers from two key issues: (1) it relies solely on geometric properties while ignoring semantic cues; (2) orientation optimization suffers from unstable gradients, causing oscillations in orientation convergence. In this paper, we propose a Fractional Semantic IoU loss to achieve unified semantic-geometric learning with gradient stabilization. First, we design a semantic similarity metric to guide IoU optimization, building a Semantic IoU loss (SIoU loss) with an adaptive gradient gating mechanism. Then, we revisit the gradient instability issue in oriented box optimization and extend the SIoU loss to a fractional-order formulation to build the \textbf{Fr}actional \textbf{S}emantic \textbf{IoU} \textbf{loss} (FrSIoU loss). The FrSIoU loss accumulates historical IoU states to regularize abnormal gradients during bounding box optimization process. Extensive experiments demonstrate that our approach achieves stable performance gains across different bounding box formulations and diverse visual detection tasks. The code will be available on GitHub.

Related papers

• MoEIoU: Rethinking Bounding-Box Regression as a Mixture of Experts [2.7501248535328315]
  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.
  arXiv  Detail & Related papers  (2026-05-30T18:34:30Z)
• IoUCert: Robustness Verification for Anchor-based Object Detectors [58.35703549470485]
  We introduce IoUCert, a novel formal verification framework designed specifically to overcome these bottlenecks in anchor-based object detection architectures.<n>We show that our method enables the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.
  arXiv  Detail & Related papers  (2026-03-03T14:36:46Z)
• 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)
• Marginalized Generalized IoU (MGIoU): A Unified Objective Function for Optimizing Any Convex Parametric Shapes [32.1114758137734]
  Marginalized Generalized IoU (MGIoU) is a novel loss function that overcomes challenges by projecting structured convex shapes onto their unique shape Normals to compute one-dimensional normalized GIoU.<n>Experiments on standard benchmarks demonstrate that MGIoU and MGIoU+ consistently outperform existing losses while reducing loss latency by 10-40x.
  arXiv  Detail & Related papers  (2025-04-23T06:05:39Z)
• Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
  Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL) This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
  arXiv  Detail & Related papers  (2024-06-09T05:57:40Z)
• Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box [10.03001043843768]
  We propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments.
  arXiv  Detail & Related papers  (2023-11-06T05:14:24Z)
• Intersection over Union with smoothing for bounding box regression [0.0]
  We focus on the construction of a loss function for the bounding box regression. The Intersection over Union (IoU) metric is improved to converge faster. We experimentally show that the proposed loss function is robust with respect to the noise in the dimension of ground truth bounding boxes.
  arXiv  Detail & Related papers  (2023-03-27T10:20:34Z)
• Rethinking IoU-based Optimization for Single-stage 3D Object Detection [103.83141677242871]
  We propose a Rotation-Decoupled IoU (RDIoU) method that can mitigate the rotation-sensitivity issue. Our RDIoU simplifies the complex interactions of regression parameters by decoupling the rotation variable as an independent term.
  arXiv  Detail & Related papers  (2022-07-19T15:35:23Z)
• Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation [56.44946660061753]
  This paper proposes a universal regularization technique called maximum spatial perturbation consistency (MSPC) MSPC enforces a spatial perturbation function (T ) and the translation operator (G) to be commutative (i.e., TG = GT ) Our method outperforms the state-of-the-art methods on most I2I benchmarks.
  arXiv  Detail & Related papers  (2022-03-23T19:59:04Z)
• Distribution-aware Margin Calibration for Semantic Segmentation in Images [78.65312390695038]
  Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. Direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable. We propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution.
  arXiv  Detail & Related papers  (2021-12-21T22:38:25Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)

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.