Pedestrian Detection by Exemplar-Guided Contrastive Learning

TL;DR

This paper introduces a novel pedestrian detection method using exemplar-guided contrastive learning to reduce appearance diversities and improve detection accuracy across various conditions.

Contribution

It proposes a contrastive learning framework guided by an exemplar dictionary to enhance feature learning for diverse pedestrian appearances.

Findings

Effective in reducing appearance diversities in pedestrian detection

Improves detection accuracy in daytime and nighttime conditions

Utilizes exemplar dictionary for proposal quality evaluation

Abstract

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.