MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing

Oct 1, 2021·

Yuhang Li

,

Feng Zhu

Ruihao Gong

Ruihao Gong

,

Mingzhu Shen

,

Xin Dong

,

Fengwei Yu

,

Shaoqing Lu

,

Shi Gu

· 0 min read

Type

Conference paper

Publication

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)

Last updated on Jun 9, 2022

Ruihao Gong

Authors

← QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization Jan 1, 2022

Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture Search Oct 1, 2021 →