Semantic segmentation based on stacked discriminative autoencoders and context-constrained weakly supervised learning

In this paper, we focus on tacking the problem of weakly supervised semantic segmentation. The aim is to predict the class label of image regions under weakly supervised settings, where training images are only provided with image-level labels indicating the classes they contain. The main difficulty of weakly supervised semantic segmentation arises from the complex diversity of visual classes and the lack of supervision information for learning a multi-classes classifier. To conquer the challenge, we propose a novel discriminative deep feature learning framework based on stacked autoencoders (SAE) by integrating pairwise constraints to serve as a discriminative term. Furthermore, to mine effective supervision information, global context about co-occurrence of visual classes as well as local context around each image region is exploited as constraints for training a multi-class classifier. Finally, the classifier training is formulated as an ultimate optimization problem, which can be solved efficiently by an alternate iterative optimization method. Comprehensive experiments on the MSRC 21 dataset demonstrate the superior performance compared with several state-of-The-Art weakly supervised image segmentation methods. Categories and Subject Descriptors I.4.6 [Image Processing and Computer Vision]: Segmentation -pixel classification; I.4.6 [Image Processing and Computer Vision]: Feature Measurement-feature representation; General Terms Algorithms, Experimentation, Performance. Keywords Semantic segmentation; Stacked autoencoders; Discriminative feature learning; Weakly supervised learning.