Scaled ReLU Matters for Training Vision Transformers

Pichao Wang, Xue Wang, Hao Luo, Jingkai Zhou, Zhipeng Zhou, Fan Wang, Hao Li, Rong Jin 0001. Scaled ReLU Matters for Training Vision Transformers. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022. pages 2495-2503, AAAI Press, 2022. [doi]

Authors

Pichao Wang

This author has not been identified. Look up 'Pichao Wang' in Google

Xue Wang

This author has not been identified. Look up 'Xue Wang' in Google

Hao Luo

This author has not been identified. Look up 'Hao Luo' in Google

Jingkai Zhou

This author has not been identified. Look up 'Jingkai Zhou' in Google

Zhipeng Zhou

This author has not been identified. Look up 'Zhipeng Zhou' in Google

Fan Wang

This author has not been identified. Look up 'Fan Wang' in Google

Hao Li

This author has not been identified. Look up 'Hao Li' in Google

Rong Jin 0001

This author has not been identified. Look up 'Rong Jin 0001' in Google