对象检测器通常在具有固定预定义类别的完全注释的训练数据上学习。然而,类别往往需要逐步增加。通常,在这种情况下,只有用旧类标注的原始训练集和一些用新类标注的新训练数据可用。基于有限的数据集,迫切需要一个能够处理所有类别的统一检测器。我们提出了一个切实可行的方案,以实现它在这项工作。无冲突损失的设计,以避免标签歧义,导致一个可接受的检测器在一个训练轮。为了进一步提高性能,我们提出了一个再训练阶段,在该阶段中,采用Monte Carlo Dropout来计算定位置信度,以挖掘更准确的边界框,并提出了一种加权的方法,以便在再训练过程中更好地利用伪注释。大量的实验证明了我们的方法的有效性。
英文摘要:
Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old classes and some new training data labeled with new classes are available in such scenarios. Based on the limited datasets, a unified detector that can handle all categories is strongly needed. We propose a practical scheme to achieve it in this work. A conflict-free loss is designed to avoid label ambiguity, leading to an acceptable detector in one training round. To further improve performance, we propose a retraining phase in which Monte Carlo Dropout is employed to calculate the localization confidence to mine more accurate bounding boxes, and an overlap-weighted method is proposed for making better use of pseudo annotations during retraining. Extensive experiments demonstrate the effectiveness of our method.
Attacking Important Pixels for Anchor-free Detectors
Chengdu University of Information Technology(成都信息工程大学);Carnegie Mellon University(卡内基梅隆大学);University at Buffalo, SUNY(纽约州立大学布法罗分校);Microsoft Research Asia(微软亚洲研究院)
Socialized Detector Learning: Trajectory-Guided and Reciprocal Distillation for Heterogeneous Object Detectors
School of New Media and Communication, Tianjin University(天津大学新媒体与传播学院);School of Artificial Intelligence, Tianjin University(天津大学人工智能学院);School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院);School of Sports Training, Tianjin University of Sport(天津体育学院运动训练学院);Faculty of Information Engineering and Automation, Kunming University of Science and Technology(昆明理工大学信息工程与自动化学院);School of Electronic Science, National University of Defense Technology(国防科技大学电子科学学院);School of Automation, Southeast University(东南大学自动化学院);School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院)
CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
National College for Excellent Engineers, Beihang University(卓越工程师学院,北京航空航天大学);AI Research, Qihoo 360(360人工智能研究院,奇虎360);School of Electronic Information Engineering, Beihang University(电子信息学院,北京航空航天大学);School of Cyber Science and Technology, Beihang University(网络安全科学与技术学院,北京航空航天大学);School of Computer Science and Engineering, Beihang University(计算机科学与工程学院,北京航空航天大学);State Key Laboratory of Media Convergence and Communication, Communication University of China(媒体融合与传播国家重点实验室,中国传媒大学);Institute of Information Technology, Mathematics and Mechanics, Lobachebsky University(信息技术、数学与力学学院,洛瓦茨基大学);School of Artificial Intelligence, Beihang University(人工智能学院,北京航空航天大学)
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology(深圳理工大学计算机科学与人工智能学院);School of Artificial Intelligence, Nanchang University(南昌大学人工智能学院)
Debiased Novel Category Discovering and Localization
Tsinghua University(清华大学);Hangzhou Zhuoxi Institute of Brain and Intelligence(杭州卓曦脑与智能研究所);OPPO Research Institute(OPPO研究院);Beijing University of Posts and Telecommunications(北京邮电大学)
Fisher-aware Quantization for DETR Detectors with Critical-category Objectives
University of California, Berkeley(加利福尼亚大学伯克利分校);Nanjing University(南京大学);Panasonic Holdings Corporation(松下控股公司);School of Computer Science, Peking University(北京大学计算机学院)
College of Information Science and Engineering, Northeastern University(信息科学与工程学院,东北大学);State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University(过程工业综合自动化国家重点实验室,东北大学)