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.
Fast Convergence of DETR with Spatially Modulated Co-Attention
Shanghai AI Laboratory(上海人工智能实验室);Peking University(北京大学);CUHK-SenseTime Joint Laboratory, The Chinese University of Hong Kong(香港中文大学-商汤科技联合实验室,香港中文大学);SenseTime Research(商汤科技研究院)
Samsung Research(三星研究院);Korea Advanced Institute of Science(韩国先进科学研究院);Department of Artificial Intelligence Software, Hanbat National University(汉巴特国立大学人工智能软件系)
PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
New York University(纽约大学);Boise State University(博伊西州立大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, Irvine(加州大学 Irvine 分校);Illinois Institute of Technology(伊利诺伊理工学院);University of Pittsburgh(匹兹堡大学)
AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection
College of Information Science and Engineering, Northeastern University(东北大学信息科学与工程学院);Foshan Graduate School of Innovation, Northeastern University(东北大学佛山创新研究生院)
Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Tongyi Lab, Alibaba Group(阿里巴巴集团通义实验室);Peng Cheng Laboratory(鹏城实验室);Pazhou Laboratory (Huangpu)(琶洲实验室(黄埔))
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images
Technical University of Kaiserslautern(凯泽斯劳滕工业大学);German Research Institute for Artificial Intelligence (DFKI)(德国人工智能研究中心);Luleå University of Technology(吕勒奥理工大学)
Tsinghua University(清华大学);International Digital Economy Academy (IDEA)(国际数字经济研究院);Alibaba Group(阿里巴巴集团);The Hong Kong University of Science and Technology(香港科技大学);South China University of Technology(华南理工大学)