Deep Learning
Relative Flatness and Generalization
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
Relative Flatness and Generalization
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
Appendix: FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling Bowen Zhang
There are 1000 iterations between every two checkpoints. SSL algorithms and the FlexMatch achieves the best accuracy. Our toolbox is partially based on [7]. More importantly, in addition to the basic SSL methods and components, we implement several techniques to make the results stable under PyTorch framework. CIFAR-100, SVHN, and STL-10, and report the best error rates in Table 6, 7, 8, and 9, respectively.
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.
bf15e9bbff22c7719020f9df4badc20a-Paper.pdf
We develop a program-guided generation technique to produce a large set of human-interpretable visual cognition problems in action-oriented LOGO language.
Isometric 3D Adversarial Examples in the Physical World Yibo Miao
Based on Definitions 1 and 2, we have the following theorem.
Full-Atom Protein Pocket Design via Iterative Refinement
The design and optimization of functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering.
Improved Transformer for High-Resolution GANs Long Zhao
To further improve the performance, we introduce an additional self-modulation component based on cross-attention.
