TwinsAdvNet : Adversarial Learning for Semantic Segmentation

Abstract

Recently, many semantic segmentation networks provide more training samples by generative adversarial networks. In practice, the generator does not simulate the detail textures of natural images, and image semantics segmentation network often has the problem of inconsistent prediction results due to small changes in network structure. In view of the above problems and the task of understanding complex scenarios, it is considered that the existing generators are not suitable for providing "real" training samples, but should be based on providing valuable label semantic information. Therefore, a two-branch semantic segmentation network, called TwinsAdvNet, which uses two kinds of predictive probability map to adversarial learning, is proposed. Its novelty is that the prediction results of one branch of segmented network are regarded as weak labels of another branch of semantic segmentation. Experimental results on MIT Scene Parsing Benchmark dataset are included to demonstrate the effectiveness of the proposed model.