Timezone: »
Transformer is a new kind of calculation paradigm for deep learning which has shown strong performance on a large variety of computer vision tasks. However, compared with conventional deep models (e.g., convolutional neural networks), vision transformers require more computational resources which cannot be easily deployed on mobile devices. To this end, we present to reduce the energy consumptions using adder neural network (AdderNet). We first theoretically analyze the mechanism of self-attention and the difficulty for applying adder operation into this module. Specifically, the feature diversity, i.e., the rank of attention map using only additions cannot be well preserved. Thus, we develop an adder attention layer that includes an additional identity mapping. With the new operation, vision transformers constructed using additions can also provide powerful feature representations. Experimental results on several benchmarks demonstrate that the proposed approach can achieve highly competitive performance to that of the baselines while achieving an about 2~3× reduction on the energy consumption.
Author Information
Han Shu (huawei noah ark's lab)
Jiahao Wang (Tsinghua University)
Hanting Chen (Peking University)
Lin Li (Huawei Technologies Co., Ltd.)
Yujiu Yang (Tsinghua University)
Yunhe Wang (Huawei Noah's Ark Lab)
More from the Same Authors
-
2021 Poster: Dynamic Resolution Network »
Mingjian Zhu · Kai Han · Enhua Wu · Qiulin Zhang · Ying Nie · Zhenzhong Lan · Yunhe Wang -
2021 Poster: Post-Training Quantization for Vision Transformer »
Zhenhua Liu · Yunhe Wang · Kai Han · Wei Zhang · Siwei Ma · Wen Gao -
2021 Poster: Handling Long-tailed Feature Distribution in AdderNets »
Minjing Dong · Yunhe Wang · Xinghao Chen · Chang Xu -
2021 Poster: Towards Stable and Robust AdderNets »
Minjing Dong · Yunhe Wang · Xinghao Chen · Chang Xu -
2021 Poster: Transformer in Transformer »
Kai Han · An Xiao · Enhua Wu · Jianyuan Guo · Chunjing XU · Yunhe Wang -
2021 Poster: An Empirical Study of Adder Neural Networks for Object Detection »
Xinghao Chen · Chang Xu · Minjing Dong · Chunjing XU · Yunhe Wang -
2021 Poster: Neural Architecture Dilation for Adversarial Robustness »
Yanxi Li · Zhaohui Yang · Yunhe Wang · Chang Xu -
2021 Poster: Learning Frequency Domain Approximation for Binary Neural Networks »
Yixing Xu · Kai Han · Chang Xu · Yehui Tang · Chunjing XU · Yunhe Wang -
2021 Poster: Augmented Shortcuts for Vision Transformers »
Yehui Tang · Kai Han · Chang Xu · An Xiao · Yiping Deng · Chao Xu · Yunhe Wang -
2021 Oral: Learning Frequency Domain Approximation for Binary Neural Networks »
Yixing Xu · Kai Han · Chang Xu · Yehui Tang · Chunjing XU · Yunhe Wang -
2020 Poster: SCOP: Scientific Control for Reliable Neural Network Pruning »
Yehui Tang · Yunhe Wang · Yixing Xu · Dacheng Tao · Chunjing XU · Chao Xu · Chang Xu -
2020 Poster: Kernel Based Progressive Distillation for Adder Neural Networks »
Yixing Xu · Chang Xu · Xinghao Chen · Wei Zhang · Chunjing XU · Yunhe Wang -
2020 Poster: Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets »
Kai Han · Yunhe Wang · Qiulin Zhang · Wei Zhang · Chunjing XU · Tong Zhang -
2020 Spotlight: Kernel Based Progressive Distillation for Adder Neural Networks »
Yixing Xu · Chang Xu · Xinghao Chen · Wei Zhang · Chunjing XU · Yunhe Wang -
2020 Poster: Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts »
Guilin Li · Junlei Zhang · Yunhe Wang · Chuanjian Liu · Matthias Tan · Yunfeng Lin · Wei Zhang · Jiashi Feng · Tong Zhang -
2020 Poster: Searching for Low-Bit Weights in Quantized Neural Networks »
Zhaohui Yang · Yunhe Wang · Kai Han · Chunjing XU · Chao Xu · Dacheng Tao · Chang Xu -
2019 Poster: Positive-Unlabeled Compression on the Cloud »
Yixing Xu · Yunhe Wang · Hanting Chen · Kai Han · Chunjing XU · Dacheng Tao · Chang Xu -
2018 Poster: Learning Versatile Filters for Efficient Convolutional Neural Networks »
Yunhe Wang · Chang Xu · Chunjing XU · Chao Xu · Dacheng Tao -
2016 Poster: CNNpack: Packing Convolutional Neural Networks in the Frequency Domain »
Yunhe Wang · Chang Xu · Shan You · Dacheng Tao · Chao Xu