Oncel Tuzel

Divide, Denoise, and Defend against Adversarial Attacks

2018 · arXiv (Cornell University)

Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important, especially …

APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations

2022 · arXiv (Cornell University)

Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets. In this work, we ask whether it is possible to achieve similar results with …