Learning to Adapt Structured Output Space for Semantic Segmentation

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to t...

Full description

Saved in:
Bibliographic Details
Published in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7472 - 7481
Main Authors: Tsai, Yi-Hsuan, Hung, Wei-Chih, Schulter, Samuel, Sohn, Kihyuk, Yang, Ming-Hsuan, Chandraker, Manmohan
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2018
Subjects:
Adaptation models
Image segmentation
Layout
Prediction algorithms
Semantics
Task analysis
Training
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00780