USDC: Unified Static and Dynamic Compression for Visual Transformer

no code implementations • 17 Oct 2023 • Huan Yuan, Chao Liao, Jianchao Tan, Peng Yao, Jiyuan Jia, Bin Chen, Chengru Song, Di Zhang

To alleviate two disadvantages of two categories of methods, we propose to unify the static compression and dynamic compression techniques jointly to obtain an input-adaptive compressed model, which can further better balance the total compression ratios and the model performances.

Model Compression

ASP: Automatic Selection of Proxy dataset for efficient AutoML

no code implementations • 17 Oct 2023 • Peng Yao, Chao Liao, Jiyuan Jia, Jianchao Tan, Bin Chen, Chengru Song, Di Zhang

Deep neural networks have gained great success due to the increasing amounts of data, and diverse effective neural network designs.

Neural Architecture Search