Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation

TL;DR

This paper introduces a Dynamic Proxy Domain method that improves the generalization of crowd localization models across different domains by using a generated proxy domain to enhance confidence-threshold learning.

Contribution

It proposes a novel domain generalization approach using a proxy domain based on theoretical analysis to improve crowd localization under domain shift.

Findings

Effective in five domain shift scenarios

Improves confidence-threshold robustness

Enhances generalization of crowd localization

Abstract

Crowd localization targets on predicting each instance precise location within an image. Current advanced methods propose the pixel-wise binary classification to tackle the congested prediction, in which the pixel-level thresholds binarize the prediction confidence of being the pedestrian head. Since the crowd scenes suffer from extremely varying contents, counts and scales, the confidence-threshold learner is fragile and under-generalized encountering domain knowledge shift. Moreover, at the most time, the target domain is agnostic in training. Hence, it is imperative to exploit how to enhance the generalization of confidence-threshold locator to the latent target domain. In this paper, we propose a Dynamic Proxy Domain (DPD) method to generalize the learner under domain shift. Concretely, based on the theoretical analysis to the generalization error risk upper bound on the latent target domain to a binary classifier, we propose to introduce a generated proxy domain to facilitate generalization. Then, based on the theory, we design a DPD algorithm which is composed by a training paradigm and proxy domain generator to enhance the domain generalization of the confidence-threshold learner. Besides, we conduct our method on five kinds of domain shift scenarios, demonstrating the effectiveness on generalizing the crowd localization. Our code will be available at https://github.com/zhangda1018/DPD.