Mini-batch graphs for robust image classification

Abstract

Current deep learning models for classification tasks in computer vision are trained using mini-batches. In the present article, we take advantage of the relationships between samples in a mini-batch, using graph neural networks to aggregate information from similar images. This helps mitigate the adverse effects of alterations to the input images on classification performance. Diverse experiments on image-based object and scene classification show that this approach not only improves a classifier's performance but also increases its robustness to image perturbations and adversarial attacks. Further, we also show that mini-batch graph neural networks can help to alleviate the problem of mode collapse in Generative Adversarial Networks.

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Improved Techniques for Training GANs
• Representation Learning on Graphs with Jumping Knowledge Networks
• Learning Convolutional Neural Networks for Graphs
• Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Simple Black-box Adversarial Attacks
• Supervised Contrastive Learning
• On GANs and GMMs