CIParsing: Unifying Causality Properties into Multiple Human Parsing

TL;DR

CIParsing introduces a causality-inspired approach to human parsing that emphasizes causal factors over spurious correlations, improving model robustness and generalization across diverse image styles and contexts.

Contribution

The paper proposes a novel causality-based paradigm for human parsing that constructs latent causal representations, enhancing robustness and generalization of existing models.

Findings

Improved parsing accuracy on benchmark datasets.

Enhanced model robustness to external interventions.

Plug-and-play integration with existing models.

Abstract

Existing methods of multiple human parsing (MHP) apply statistical models to acquire underlying associations between images and labeled body parts. However, acquired associations often contain many spurious correlations that degrade model generalization, leading statistical models to be vulnerable to visually contextual variations in images (e.g., unseen image styles/external interventions). To tackle this, we present a causality inspired parsing paradigm termed CIParsing, which follows fundamental causal principles involving two causal properties for human parsing (i.e., the causal diversity and the causal invariance). Specifically, we assume that an input image is constructed by a mix of causal factors (the characteristics of body parts) and non-causal factors (external contexts), where only the former ones cause the generation process of human parsing.Since causal/non-causal factors are unobservable, a human parser in proposed CIParsing is required to construct latent representations of causal factors and learns to enforce representations to satisfy the causal properties. In this way, the human parser is able to rely on causal factors w.r.t relevant evidence rather than non-causal factors w.r.t spurious correlations, thus alleviating model degradation and yielding improved parsing ability. Notably, the CIParsing is designed in a plug-and-play fashion and can be integrated into any existing MHP models. Extensive experiments conducted on two widely used benchmarks demonstrate the effectiveness and generalizability of our method.