Semi-supervised semantic segmentation via image-to-image translation

Feilong Wu; Suya You

doi:10.1117/12.2586052

12 April 2021 Semi-supervised semantic segmentation via image-to-image translation

Feilong Wu, Suya You

Proceedings Volume 11729, Automatic Target Recognition XXXI; 117290E (2021) https://doi.org/10.1117/12.2586052
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Semantic segmentation is an important task in computer vision that aims to infer pixel-level semantic label information in images. Recently significant progresses have been made in deep neural networks-driven segmentation techniques, but these often require a large number of labels to supervise neural network training. Obtaining a sufficient number of labeled training data is challenging and sometimes impractical in real-world applications. This paper aims to study a semi-supervised semantic segmentation via image-to-image (I2I) translation technique. I2I is an emerging technique that maps an image from a domain to another domain. We uniquely treat the image semantic segmentation as an I2I translation task that infers semantic labels of objects (target domain) from input image (source domain) in a weakly supervised way. Particularly, we develop a two-pass strategy of I2I combining images with real and pseudo labels for semi-supervised model learning. The first pass uses unsupervised models to generate pseudo labels that combine with inputs to form pseudo-labeled samples. Since the pseudo-labeled images may undermine the quality of the model, they have to be specifically constrained in training by a noise correction framework to ensure good performance. Therefore, we boost the performance by incorporating both real and the pseudo labeled samples into the second pass to train a model based on a supervised architecture. Our goal is to bridge the gap between supervised and unsupervised learning for semantic object segmentation in practical. Extensive evaluations are conducted to demonstrate the efficiency and effectiveness of the proposed technique.

Conference Presentation

Citation Download Citation

Feilong Wu and Suya You "Semi-supervised semantic segmentation via image-to-image translation", Proc. SPIE 11729, Automatic Target Recognition XXXI, 117290E (12 April 2021); https://doi.org/10.1117/12.2586052

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available