不用匈牙利算法，用注意力自动匹配目标，提速超50%
Beyond Hungarian: Match-Free Supervision for End-to-End Object Detection
- 用跨注意力机制自动选择查询，替代传统匹配
- 训练效率提升，匹配延迟降低50%以上
- 适合追求高效训练的检测模型研究者
基于DETR的检测框架在端到端目标检测中取得显著成果。然而，依赖匈牙利算法进行查询与真实框之间的二分匹配带来了计算开销，并使训练动态复杂化。本文提出一种新型无匹配训练方案，彻底消除显式启发式匹配需求。核心是设计一个基于交叉注意力的查询选择（CAQS）模块，利用编码后的真值信息通过交叉注意力机制探测解码器查询。通过最小化查询结果与真值间的加权误差，模型自主学习查询与目标间的隐式对应关系，并进一步为查询学习提供监督信号。实验表明，该方法跳过传统匹配流程，显著提升训练效率，匹配延迟降低超过50%，通过可微对应学习有效消除离散匹配瓶颈，且性能优于现有最先进方法。
原文摘要 · Abstract (English)
Recent DEtection TRansformer (DETR) based frameworks have achieved remarkable success in end-to-end object detection. However, the reliance on the Hungarian algorithm for bipartite matching between queries and ground truths introduces computational overhead and complicates the training dynamics. In this paper, we propose a novel matching-free training scheme for DETR-based detectors that eliminates the need for explicit heuristic matching. At the core of our approach is a dedicated Cross-Attention-based Query Selection (CAQS) module. Instead of discrete assignment, we utilize encoded ground-truth information to probe the decoder queries through a cross-attention mechanism. By minimizing the weighted error between the queried results and the ground truths, the model autonomously learns the implicit correspondences between object queries and specific targets. This learned relationship further provides supervision signals for the learning of queries. Experimental results demonstrate that our proposed method bypasses the traditional matching process, significantly enhancing training efficiency, reducing the matching latency by over 50\%, effectively eliminating the discrete matching bottleneck through differentiable correspondence learning, and also achieving superior performance compared to existing state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。