Contrastive JS: A Novel Scheme for Enhancing the Accuracy and Robustness of Deep Models

Abstract

Deep learning technologies have been applied in various computer vision tasks in recent years. However, deep models suffer performance decay when some unforeseen data are contained in the testing dataset. Although data enhancement techniques can alleviate this dilemma, the diversity of real data is too tremendous to simulate. To tackle this challenge, we study a scheme for improving the robustness and efficiency of the deep network training process in visual tasks. Specifically, first, we build positive and negative sample pairs based on a class-sensitive strategy. Then, we construct a feature-consistent learning strategy based on contrastive learning to constrain the representations of interclass features while paying attention to the intraclass features. To extend the effect of the consistent strategy, we propose a novel contrastive Jensen-Shannon divergence consistency loss (JS loss) to restrict the probability distributions of different sample pairs. The proposed scheme successfully enhances the robustness and accuracy of the utilized model. We validated our approach by conducting extensive experiments in the domains of model robustness and few-shot object detection (FSOD). The results showed that the proposed method achieved remarkable gains over state-of-the-art (SOTA) methods. We obtained a 3.2% average improvement over the best-performing FSOD method.