arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.09247cs.CV
收藏

将多种分配策略整合进DETRs

Integrating Diverse Assignment Strategies into DETRs

Yiwei Zhang, Jin Gao, Hanshi Wang, Fudong Ge, Guan Luo, Weiming Hu, Zhipeng Zhang

AI总结:

LoRA-DETR通过整合多种分配策略提升检测性能,实现轻量高效且无需额外计算成本的改进。

摘要:

标签分配是对象检测器中的关键组成部分,特别是在DETR风格的框架中,尽管一对一匹配策略因其端到端的优雅而备受推崇,但其收敛速度慢是由于监督信号稀疏所致。虽然近期的研究探索了一对多分配以丰富监督信号,但它们通常引入复杂的、架构特定的修改,并通常只关注单一辅助策略,缺乏统一且可扩展的设计。在本文中,我们首先系统地研究了“一对多”监督的影响,并揭示了一个令人惊讶的发现:性能提升并非由监督量的多少驱动,而是由所采用的分配策略的多样性驱动。这一发现表明,一种更优雅、参数更高效的途径是可行的。基于这一见解,我们提出了LoRA-DETR,一种灵活且轻量的框架,能够无缝地将多种分配策略整合到任何DETR风格的检测器中。我们的方法在训练过程中通过多个低秩适应(LoRA)分支增强主要网络,每个分支实例化不同的“一对多”分配规则。这些分支作为辅助模块,将丰富的、多样的监督梯度注入到主模型中,并在推理时被丢弃,从而不增加额外的计算成本。这种设计促进了稳健的联合优化,同时保持了原始检测器的架构简洁性。在不同基线上的广泛实验验证了我们方法的有效性。我们的工作提出了一种增强检测器的新范式,证明了通过整合多样化的“一对多”监督可以实现最先进的结果,而无需牺牲模型的优雅性。

英文摘要:

Label assignment is a critical component in object detectors, particularly within DETR-style frameworks where the one-to-one matching strategy, despite its end-to-end elegance, suffers from slow convergence due to sparse supervision. While recent works have explored one-to-many assignments to enrich supervisory signals, they often introduce complex, architecture-specific modifications and typically focus on a single auxiliary strategy, lacking a unified and scalable design. In this paper, we first systematically investigate the effects of ``one-to-many'' supervision and reveal a surprising insight that performance gains are driven not by the sheer quantity of supervision, but by the diversity of the assignment strategies employed. This finding suggests that a more elegant, parameter-efficient approach is attainable. Building on this insight, we propose LoRA-DETR, a flexible and lightweight framework that seamlessly integrates diverse assignment strategies into any DETR-style detector. Our method augments the primary network with multiple Low-Rank Adaptation (LoRA) branches during training, each instantiating a different one-to-many assignment rule. These branches act as auxiliary modules that inject rich, varied supervisory gradients into the main model and are discarded during inference, thus incurring no additional computational cost. This design promotes robust joint optimization while maintaining the architectural simplicity of the original detector. Extensive experiments on different baselines validate the effectiveness of our approach. Our work presents a new paradigm for enhancing detectors, demonstrating that diverse ``one-to-many'' supervision can be integrated to achieve state-of-the-art results without compromising model elegance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑