Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples

no code implementations • 6 Jun 2024 • Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong

We further prove that this shared principle is the key to their success-achieve small test error within a small labeled set.

Mask-Embedded Discriminator With Region-Based Semantic Regularization for Semi-Supervised Class-Conditional Image Synthesis

no code implementations • CVPR 2021 • Yi Liu, Xiaoyang Huo, Tianyi Chen, Xiangping Zeng, Si Wu, Zhiwen Yu, Hau-San Wong

Semi-supervised generative learning (SSGL) makes use of unlabeled data to achieve a trade-off between the data collection/annotation effort and generation performance, when adequate labeled data are not available.

Generative Adversarial Network Image Generation

Towards a Mathematical Foundation of Immunology and Amino Acid Chains

2 code implementations • 28 May 2012 • Wen-Jun Shen, Hau-San Wong, Quan-Wu Xiao, Xin Guo, Stephen Smale

We attempt to set a mathematical foundation of immunology and amino acid chains.

Clustering