Title: Digging Into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation 

Author(s): Chen, ZH (Chen, Zhenghao); Zhang, R (Zhang, Rui); Zhang, G (Zhang, Gang); Ma, ZH (Ma, Zhenhuan); Lei, T (Lei, Tao) 

Source: IEEE ACCESS  Volume: 8  Pages: 41830-41837  DOI: 10.1109/ACCESS.2020.2975022  Published: 2020   

Abstract: The capability to understand visual scenes with limited labeled data has been widely concerned in the field of computer vision. Although semi-supervised learning for image classification has been extensively studied in some cases, semantic segmentation with limited data has only recently gained attention. In this work, we follow the standard semi-supervised segmentation pipeline for image classification and propose a two-branch network that can encode strong and pseudo label spaces respectively, extracting reliable supervision information from pseudo-labels to assist in training network with strong labels. Our method outperforms previous semi-supervised methods with limited annotation cost. On standard benchmark PASCAL VOC 2012 for semi-supervised semantic segmentation, the proposed approach gains fresh state-of-the-art performance. 

ISSN: 2169-3536