ARBiBench: Benchmarking and Analyzing Adversarial Robustness of Binarized Convolutional Neural Networks
Binarized convolutional neural networks (BCNNs), which restrict the weights and activations of the model to + 1 or −1, provide notable reductions […]
Learning Binary-Antithetical Information Bottleneck for Generalizable Face Anti-Spoofing
We investigate generalizable face anti-spoofing (FAS) using information bottleneck theory. As generalizable FAS aims to detect spoofing in unseen scenarios, it has […]
Importance-Aware Information Bottleneck Learning Paradigm for Lip Reading
Lip reading is the task of decoding text from speakers’ mouth movements. Numerous deep learning-based methods have been proposed to address this […]