Debiased Novel Category Discovering and Localization
This work addresses the challenge of detecting and localizing novel object categories in deep learning-based object detection, which is crucial for real-world applications where not all categories are predefined, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of Novel Class Discovery and Localization (NCDL) in object detection, where existing models fail to detect unseen categories, and proposes a Debiased Region Mining (DRM) approach that significantly outperforms previous methods, establishing a new state-of-the-art on the NCDL benchmark.
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.