Attentively Conditioned Generative Adversarial Network for Semantic Segmentation

Generative Adversarial Network has proven to produce state-of-the-art results by framing a generative modeling task into a supervised learning problem. In this paper, we propose Attentively Conditioned Generative Adversarial Network (ACGAN) for semantic segmentation by designing a segmentor model that generates probability maps from images and a discriminator model which discriminates the segmentor's output from the ground truth labels. Additionally, we conditioned the discriminator's dual inputs with extra information as a conditional adversarial model such that, an attention obtained probability distribution of the segmentor's feature maps is incorporated, and the ground truth is also accompanied by a vector of the class label. We demonstrate that our proposed model can provide better semantic segmentation results while stabilizing the discriminator to model long-range dependencies as a result of the supplementary inputs to the network. The attention network particularly provides more insights by extracting cues from the feature locations, and alongside the class label vector, gives the model an advantage to inform better spectral sensitivity. Experiments on the PASCAL VOC 2012 and the CamVid datasets show that our adversarial training technique yields improved accuracy.