Pedestrian Detection by Exemplar-Guided Contrastive Learning

11/17/2021
by   Zebin Lin, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 9

research
09/20/2023

PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving

Pedestrian detection under valet parking scenarios is fundamental for au...
research
04/12/2023

Learning Transferable Pedestrian Representation from Multimodal Information Supervision

Recent researches on unsupervised person re-identification (reID) have d...
research
10/03/2016

Real-Time RGB-D based Template Matching Pedestrian Detection

Pedestrian detection is one of the most popular topics in computer visio...
research
11/04/2019

A Comprehensive Study on Pedestrians' Evacuation

Human beings face threats because of unexpected happenings, which can be...
research
08/23/2023

Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection

RGB-Thermal (RGB-T) pedestrian detection aims to locate the pedestrians ...
research
12/12/2022

CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection

Pedestrian detection in the wild remains a challenging problem especiall...
research
12/02/2022

Learning a Pedestrian Social Behavior Dictionary

Understanding pedestrian behavior patterns is a key component to buildin...

Please sign up or login with your details

Forgot password? Click here to reset