Recent research on universal object detection aims to introduce language in a SoTA closed-set detector and then generalize the open-set concepts by constructing large-scale (text-region) datasets for training. However, these methods face two main challenges: (i) how to efficiently use the prior information in the prompts to genericise objects and (ii) how to reduce alignment bias in the downstream tasks, both leading to sub-optimal performance in some scenarios beyond pre-training. To address these challenges, we propose a strong universal detection foundation model called CP-DETR, which is competitive in almost all scenarios, with only one pre-training weight. Specifically, we design an efficient prompt visual hybrid encoder that enhances the information interaction between prompt and visual through scale-by-scale and multi-scale fusion modules. Then, the hybrid encoder is facilitated to fully utilize the prompted information by prompt multi-label loss and auxiliary detection head. In addition to text prompts, we have designed two practical concept prompt generation methods, visual prompt and optimized prompt, to extract abstract concepts through concrete visual examples and stably reduce alignment bias in downstream tasks. With these effective designs, CP-DETR demonstrates superior universal detection performance in a broad spectrum of scenarios. For example, our Swin-T backbone model achieves 47.6 zero-shot AP on LVIS, and the Swin-L backbone model achieves 32.2 zero-shot AP on ODinW35. Furthermore, our visual prompt generation method achieves 68.4 AP on COCO val by interactive detection, and the optimized prompt achieves 73.1 fully-shot AP on ODinW13.
UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects
Easy Lab, College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China(易实验室,数学与信息学院,华南农业大学,广州,中国);School of Computer Science and Engineering, Southeast University, Nanjing, China(计算机科学与工程学院,东南大学,南京,中国);School of Mathematics, Foshan University, Foshan, China(数学学院,佛山大学,佛山,中国)
Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学);Information Technology University(信息技术大学);Australian National University(澳大利亚国立大学);Linköping University(林雪平大学)
Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection
Multimedia Laboratory, The Chinese University of HongKong(香港中文大学多媒体实验室);SenseTime Research(商汤科技研究院);Centre for Perceptual and Interactive Intelligence Limited(感知与交互智能中心有限公司);Shanghai AI Laboratory(上海人工智能实验室)
VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
School of Information and Electronics, Beijing Institute of Technology(信息与电子学院,北京理工大学);Beijing Institute of Technology Chongqing Innovation Center(北京理工大学重庆创新中心);National Key Laboratory for Space-Born Intelligent Information Processing(空间智能信息处理国家重点实验室)
RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models
School of Electronic and Computer Engineering, Peking University, Shenzhen, China(北京大学电子与计算机工程学院,深圳,中国);Department of Automation and BNRist, Tsinghua University, Beijing, China(清华大学自动化系及BNRist,北京,中国)
ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection
School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院)
Detection of On-Ground Chestnuts Using Artificial Intelligence Toward Automated Picking
School of Automation Engineering, University of Electronic Science;Department of Biosystems \& Agricultural Engineering, Michigan State University, East Lansing, MI 48824, United States
CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection
School of Computing and Data Science, The University of Hong Kong(计算与数据科学学院,香港大学);Department of Electrical & Computer Engineering, National University of Singapore(电气与计算机工程系,新加坡国立大学);School of Information and Electronics, Beijing Institute of Technology(信息与电子学院,北京理工大学)
What Are Expected Queries in End-to-End Object Detection?
Shanghai AI Laboratory(上海人工智能实验室);SenseTime Research(商汤科技研究院)
端到端的目标检测在DETR出现后得到了迅速的发展。DETR使用一组稀疏查询来取代大多数传统检测器中的密集候选框。相比之下,稀疏查询不能保证高召回密集先验。然而,在当前的框架中,使查询密集并不是微不足道的。它不仅计算量大,而且优化困难。由于稀疏查询和密集查询都是不完美的,那么\emph{what are expected queries in end-to-end object detection}?本文表明,预期的查询应该是密集的独特的查询(DDQ)。具体地说,我们引入密集先验的框架生成密集查询。重复查询移除预处理应用于这些查询,使得它们彼此可区分。然后迭代地处理密集的不同查询以获得最终的稀疏输出。我们表明,DDQ是更强大,更强大,收敛速度更快。它在MS COCO检测数据集上仅用12个时期获得44.5 AP。DDQ也是鲁棒的,因为它在各种数据集上的目标检测和实例分割任务上都优于以前的方法。DDQ融合了传统的密集先验和最近的端到端检测器的优点。我们希望它可以作为一个新的基线,并激励研究人员重新审视传统方法和端到端检测器之间的互补性。源代码可在\url{https://github.com/jshilong/DDQ}上公开获得。
Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening
State Key Laboratory of Advanced Medical Materials and Devices(先进医用材料与器件国家重点实验室);School of Biomedical Engineering, Shanghai Jiao Tong University(上海交通大学生物医学工程学院);Shanghai Clinical Research and Trial Center(上海临床研究与试验中心)
High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
Institute of Cyberspace Security, Harbin Institute of Technology, Shenzhen(网络安全研究所,哈尔滨工业大学,深圳);Department of New Networks, Peng Cheng Laboratory(新网络部门,鹏城实验室);School of Cyberspace Science, Harbin Institute of Technology(空间科学学院,哈尔滨工业大学);Center on Machine Learning Research, Harbin Institute of Technology(机器学习研究中心,哈尔滨工业大学);Faculty of Information Technology, Monash University(信息技术学院,墨尔本大学)
Image Processing Center, Beihang University(北京航空航天大学图像处理中心);State Key Laboratory of High-Efficiency Reusable Aerospace Transportation Technology(高效可重复使用航天运输技术国家重点实验室);Department of Ultrasound, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College(中国医学科学院肿瘤医院超声科);State Key Laboratory of Virtual Reality Technology and Systems, Ministry of Education(虚拟现实技术与系统国家重点实验室);the Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technology, Ministry of Education(航天器设计优化与动态仿真技术重点实验室)
Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);ShanghaiTech University(上海科技大学);Beijing Institute of Basic Medical Sciences(北京基础医学研究所)
GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval
College of Electronics and Information Engineering, Sichuan University(四川大学电子信息工程学院);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院)
DExTeR: Weakly Semi-Supervised Object Detection with Class and Instance Experts for Medical Imaging
University of Strasbourg, CNRS, INSERM, ICube, UMR7357, France(斯特拉斯堡大学、法国国家科学研究中心、法国国家医学研究院、ICube、UMR7357、法国);University Hospital of Strasbourg, France(斯特拉斯堡大学医院、法国)