Debiased Novel Category Discovering and Localization

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.

Authors

• Juexiao Feng Tsinghua University BNRist Hangzhou Zhuoxi Institute of Brain and Intelligence
• Yuhong Yang Tsinghua University BNRist Hangzhou Zhuoxi Institute of Brain and Intelligence
• Yanchun Xie OPPO Research Institute
• Yaqian Li OPPO Research Institute
• Yandong Guo AI2 Robotics
• Yuchen Guo Tsinghua University BNRist
• Yuwei He Tsinghua University BNRist
• Liuyu Xiang BUPT
• Guiguang Ding School of Software, Tsinghua University

Keywords

• CV: Applications
• CV: Object Detection & Categorization
• CV: Representation Learning for Vision