Mini-batch graphs for robust image classification
This work addresses robustness issues in computer vision for image classification tasks, representing an incremental improvement by applying graph neural networks to mini-batch structures.
The authors tackled the problem of improving robustness in image classification by leveraging relationships between samples in mini-batches using graph neural networks, resulting in enhanced performance and resilience to perturbations and adversarial attacks.
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.