# Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

arXiv: https://arxiv.org/abs/1801.01260 · HTML: https://mlsanity.com/paper/1801.01260/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2018.

## Built on by (most cited first, 11 of 11)

- [Part-aware Panoptic Segmentation](https://mlsanity.com/paper/2106.06351/) (2021)
- [Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation](https://mlsanity.com/paper/2204.04655/) (2022)
- [Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing](https://mlsanity.com/paper/2103.04570/) (2021)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition](https://mlsanity.com/paper/2204.04654/) (2022)
- [Multi-task Fusion for Efficient Panoptic-Part Segmentation](https://mlsanity.com/paper/2212.07671/) (2022)
- [Learning Part Segmentation from Synthetic Animals](https://mlsanity.com/paper/2311.18661/) (2023)
- [Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis](https://mlsanity.com/paper/2305.19547/) (2023)
- [JPPF: Multi-task Fusion for Consistent Panoptic-Part Segmentation](https://mlsanity.com/paper/2311.18618/) (2023)
- [Deep Learning for Human Parsing: A Survey](https://mlsanity.com/paper/2301.12416/) (2023)
- [Exploring the Robustness of Human Parsers Towards Common Corruptions](https://mlsanity.com/paper/2309.00938/) (2023)

## Abstract (arXiv)

Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduce the discrepancy between feature distributions of two domains. Besides, our model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the cross-domain human parsing problem.