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

TL;DR

This paper introduces a differentiable NMS method using Sinkhorn matching for fabric defect detection, enabling end-to-end training, improved localization, and adaptability to various architectures and tasks.

Contribution

It reformulates NMS as a differentiable bipartite matching problem solved by Sinkhorn-Knopp, allowing gradient flow and enhancing defect localization accuracy.

Findings

Significant performance improvements on Tianchi fabric defect dataset

Maintains real-time speeds suitable for industrial use

Generalizes effectively to other object detection tasks

Abstract

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.