3 accepted papers
Adversarial training (AT) enhances neural network robustness. Typically, AT updates all trainable parameters, but can lead to overfitting and increased errors on clean data. Research suggests that fine-tuning specific parameters may be more effective; however, methods for identifying these essential…
Vision transformers (ViTs) have become essential backbones in advanced computer vision applications and multi-modal foundation models. Despite their strengths, ViTs remain vulnerable to adversarial perturbations, comparable to or even exceeding the vulnerability of convolutional neural networks (CNN…
Search spaces hallmark the advancement of Neural Architecture Search (NAS). Large and complex search spaces with versatile building operators and structures provide more opportunities to brew promising architectures, yet pose severe challenges on efficient exploration and exploitation. Subsequently,…