Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization

TL;DR

This paper investigates how scale shift affects crowd localization under domain generalization, providing a benchmark, theoretical analysis, and a novel method to mitigate scale shift effects.

Contribution

It offers the first comprehensive analysis of scale shift in crowd localization for domain generalization, introduces ScaleBench benchmark, and proposes the Catto algorithm to address scale shift challenges.

Findings

Existing algorithms have limitations under scale shift.

Scale shift significantly impacts crowd localization performance.

The proposed Catto method effectively mitigates scale shift influence.

Abstract

Crowd localization plays a crucial role in visual scene understanding towards predicting each pedestrian location in a crowd, thus being applicable to various downstream tasks. However, existing approaches suffer from significant performance degradation due to discrepancies in head scale distributions (scale shift) between training and testing data, a challenge known as domain generalization (DG). This paper aims to comprehend the nature of scale shift within the context of domain generalization for crowd localization models. To this end, we address four critical questions: (i) How does scale shift influence crowd localization in a DG scenario? (ii) How can we quantify this influence? (iii) What causes this influence? (iv) How to mitigate the influence? Initially, we conduct a systematic examination of how crowd localization performance varies with different levels of scale shift. Then, we establish a benchmark, ScaleBench, and reproduce 20 advanced DG algorithms to quantify the influence. Through extensive experiments, we demonstrate the limitations of existing algorithms and underscore the importance and complexity of scale shift, a topic that remains insufficiently explored. To deepen our understanding, we provide a rigorous theoretical analysis on scale shift. Building on these insights, we further propose an effective algorithm called Causal Feature Decomposition and Anisotropic Processing (Catto) to mitigate the influence of scale shift in DG settings. Later, we also provide extensive analytical experiments, revealing four significant insights for future research. Our results emphasize the importance of this novel and applicable research direction, which we term Scale Shift Domain Generalization.