Channel-wise quantization without accuracy degradation using Δloss analysis

Kazuki Okado, Kengo Matsumoto, Atsuki Inoue, Hiroshi Kawaguchi, Yasufumi Sakai. Channel-wise quantization without accuracy degradation using Δloss analysis. In ICMLT 2022: 7th International Conference on Machine Learning Technologies, Rome, Italy, March 11 - 13, 2022. pages 56-61, ACM, 2022. [doi]

Authors

Kazuki Okado

This author has not been identified. Look up 'Kazuki Okado' in Google

Kengo Matsumoto

This author has not been identified. Look up 'Kengo Matsumoto' in Google

Atsuki Inoue

This author has not been identified. Look up 'Atsuki Inoue' in Google

Hiroshi Kawaguchi

This author has not been identified. Look up 'Hiroshi Kawaguchi' in Google

Yasufumi Sakai

This author has not been identified. Look up 'Yasufumi Sakai' in Google