# Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection

arXiv: https://arxiv.org/abs/2505.07040 · HTML: https://mlsanity.com/paper/2505.07040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 11 May 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [Bounding Box Regression with Uncertainty for Accurate Object Detection](https://mlsanity.com/paper/1809.08545/) (2018)
- [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017)
- [Revisiting the Sibling Head in Object Detector](https://mlsanity.com/paper/2003.07540/) (2020)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2201.00464/) (2022)
- [Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection](https://mlsanity.com/paper/2412.17458/) (2024)
- [FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings](https://mlsanity.com/paper/2002.07662/) (2020)
- [Work-Efficient Parallel Non-Maximum Suppression Kernels](https://mlsanity.com/paper/2502.00535/) (2025)

## Built on by (most cited first, 3 of 3)

- [Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models](https://mlsanity.com/paper/2603.21389/) (2026)
- [Language-Driven Coordination and Learning in Multi-Agent Simulation Environments](https://mlsanity.com/paper/2506.04251/) (2025)
- [BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation](https://mlsanity.com/paper/2603.05921/) (2026)

## Abstract (arXiv)

Fabric defect detection confronts two fundamental challenges. First, conventional non-maximum suppression disrupts gradient flow, which hinders genuine end-to-end learning. Second, acquiring pixel-level annotations at industrial scale is prohibitively costly. Addressing these limitations, we propose a differentiable NMS framework for fabric defect detection that achieves superior localization precision through end-to-end optimization. We reformulate NMS as a differentiable bipartite matching problem solved through the Sinkhorn-Knopp algorithm, maintaining uninterrupted gradient flow throughout the network. This approach specifically targets the irregular morphologies and ambiguous boundaries of fabric defects by integrating proposal quality, feature similarity, and spatial relationships. Our entropy-constrained mask refinement mechanism further enhances localization precision through principled uncertainty modeling. Extensive experiments on the Tianchi fabric defect dataset demonstrate significant performance improvements over existing methods while maintaining real-time speeds suitable for industrial deployment. The framework exhibits remarkable adaptability across different architectures and generalizes effectively to general object detection tasks.