Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

01/04/2018
by   Si Liu, et al.
0

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.

READ FULL TEXT
research
03/20/2023

Unsupervised Cross-Domain Rumor Detection with Contrastive Learning and Cross-Attention

Massive rumors usually appear along with breaking news or trending topic...
research
10/22/2022

Cross-domain Generalization for AMR Parsing

Abstract Meaning Representation (AMR) parsing aims to predict an AMR gra...
research
09/16/2018

Cross-Domain Labeled LDA for Cross-Domain Text Classification

Cross-domain text classification aims at building a classifier for a tar...
research
03/10/2023

Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D c...
research
02/28/2023

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

Opinion target extraction (OTE) or aspect extraction (AE) is a fundament...
research
08/08/2019

Neural Network based Deep Transfer Learning for Cross-domain Dependency Parsing

In this paper, we describe the details of the neural dependency parser s...
research
11/03/2019

Multi-marginal Wasserstein GAN

Multiple marginal matching problem aims at learning mappings to match a ...

Please sign up or login with your details

Forgot password? Click here to reset