.png){kind=icon}
返回
CPI-Parser: Integrating Causal Properties Into Multiple Human Parsing
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2024.3469579.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing methods of multiple human parsing (MHP) apply deep models to learn instance-level representations for segmenting each person into non-overlapped body parts. However, learned representations often contain many spurious correlations that degrade model generalization, leading learned models to be vulnerable to visually contextual variations in images (e.g., unseen image styles/external interventions). To tackle this, we present a causal property integrated parsing model termed CPI-Parser, which is driven by fundamental causal principles involving two causal properties for human parsing (i.e., the causal diversity and the causal invariance). Specifically, we assume that an 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 decide the essence of human parsing. Since causal/non-causal factors are unobservable, the proposed CPI-Parser is required to separate key factors that satisfy the causal properties from an image. In this way, the 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 CPI-Parser is designed in a flexible way and can be integrated into any existing MHP frameworks. Extensive experiments conducted on three widely used benchmarks demonstrate the effectiveness and generalizability of our method. Code and models are released (https://github.com/HAG-uestc/CPI-Parser) for research purpose.
Keyword:
Correlation
Semantics
Context modeling
Representation learning
Image segmentation
Degradation
Visualization
Pipelines
Image reconstruction
Data models
Multiple human parsing
causal representation learning
human-centric dense recognition
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
Contrastive-ACE: Domain Generalization Through Alignment of Causal Mechanisms对比-ACE: 通过因果机制的对齐进行域泛化
OAAI
OAAI分享收藏
查看更多内容