Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 32, Issue -, Pages 2003-2016Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2022.3189803
Keywords
Feature extraction; Proposals; Semantics; Dictionaries; Detectors; Adaptation models; Object detection; Pedestrian detection; contrastive learning
Ask authors/readers for more resources
Typical methods for pedestrian detection focus on tackling occlusions between crowded pedestrians or dealing with various scales. However, detecting pedestrians with diverse appearances remains challenging. This proposed method introduces contrastive learning to guide feature learning by minimizing semantic distance between pedestrians with different appearances while maximizing distance between pedestrians and background. An exemplar dictionary is also constructed to facilitate efficient and effective contrastive learning and evaluate pedestrian proposals.
Typical methods for pedestrian detection focus on either tackling mutual occlusions between crowded pedestrians, or dealing with the various scales of pedestrians. Detecting pedestrians with substantial appearance diversities such as different pedestrian silhouettes, different viewpoints or different dressing, remains a crucial challenge. Instead of learning each of these diverse pedestrian appearance features individually as most existing methods do, we propose to perform contrastive learning to guide the feature learning in such a way that the semantic distance between pedestrians with different appearances in the learned feature space is minimized to eliminate the appearance diversities, whilst the distance between pedestrians and background is maximized. To facilitate the efficiency and effectiveness of contrastive learning, we construct an exemplar dictionary with representative pedestrian appearances as prior knowledge to construct effective contrastive training pairs and thus guide contrastive learning. Besides, the constructed exemplar dictionary is further leveraged to evaluate the quality of pedestrian proposals during inference by measuring the semantic distance between the proposal and the exemplar dictionary. Extensive experiments on both daytime and nighttime pedestrian detection validate the effectiveness of the proposed method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available