Learning to Match Anchors for Visual Object Detection

• Published in: IEEE transactions on pattern analysis and machine intelligence 2022-06, Vol.44 (6), p.3096-3109
• Main Authors: Zhang, Xiaosong, Wan, Fang, Liu, Chang, Ji, Xiangyang, Ye, Qixiang
• Format: Article
• Language: English
• Subjects: Algorithms; anchor-free detector; Detectors; Feature extraction; generalized linear model; Learning; learning to match; Location awareness; Matching; Maximum likelihood estimation; Neural Networks, Computer; Object detection; Object recognition; Sensors; Training; Visualization
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2021.3050494

Modern CNN-based object detectors assign anchors for ground-truth objects under the restriction of object-anchor Intersection-over-Union (IoU). In this study, we propose a learning-to-match (LTM) method to break IoU restriction, allowing objects to match anchors in a flexible manner. LTM updates hand-crafted anchor assignment to "free" anchor matching by formulating detector training in the Maximum Likelihood Estimation (MLE) framework. During the training phase, LTM is implemented by converting the detection likelihood to anchor matching loss functions which are plug-and-play. Minimizing the matching loss functions drives learning and selecting features which best explain a class of objects with respect to both classification and localization. LTM is extended from anchor-based detectors to anchor-free detectors, validating the general applicability of learnable object-feature matching mechanism for visual object detection. Experiments on MS COCO dataset demonstrate that LTM detectors consistently outperform counterpart detectors with significant margins. The last but not the least, LTM requires negligible computational cost in both training and inference phases as it does not involve any additional architecture or parameter. Code has been made publicly available.