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

arXiv: https://arxiv.org/abs/2607.23530 · HTML: https://mlsanity.com/paper/2607.23530/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 53 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Rotation-Sensitive Regression for Oriented Scene Text Detection](https://mlsanity.com/paper/1803.05265/) (2018)
- [FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding](https://mlsanity.com/paper/2401.01970/) (2024)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [Dynamic Anchor Learning for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2012.04150/) (2020)
- [Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors](https://mlsanity.com/paper/2008.07043/) (2020)
- [PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments](https://mlsanity.com/paper/2007.09584/) (2020)
- [Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism](https://mlsanity.com/paper/2301.10051/) (2023)
- [Rethinking IoU-based Optimization for Single-stage 3D Object Detection](https://mlsanity.com/paper/2207.09332/) (2022)
- [Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks](https://mlsanity.com/paper/1804.06039/) (2018)
- [Rethinking Boundary Discontinuity Problem for Oriented Object Detection](https://mlsanity.com/paper/2305.10061/) (2023)
- [Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances](https://mlsanity.com/paper/2502.04268/) (2025)
- [OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images](https://mlsanity.com/paper/2409.19648/) (2024)

## Abstract (arXiv)

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 Fractional Semantic IoU 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.