Deep Learning
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks.
Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
We show that both techniques can be well incorporated into the sparse training algorithm to form a generic framework, which we dub SpFDE.
Robust Pre-Training by Adversarial Contrastive Learning
This fits particularly well with the goal of adversarial robustness, as one cause of adversarial fragility is the lack of feature invariance, i.e., small input perturbations can
Understanding and Improving Fast Adversarial Training
A recent line of work focused on making adversarial training computationally efficient for deep learning models.
