Contextual Transformer Networks for Visual Recognition

26 Jul 2021  ·  Yehao Li, Ting Yao, Yingwei Pan, Tao Mei ·

Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer (CoT) block, for visual recognition. Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation. Technically, CoT block first contextually encodes input keys via a $3\times3$ convolution, leading to a static contextual representation of inputs. We further concatenate the encoded keys with input queries to learn the dynamic multi-head attention matrix through two consecutive $1\times1$ convolutions. The learnt attention matrix is multiplied by input values to achieve the dynamic contextual representation of inputs. The fusion of the static and dynamic contextual representations are finally taken as outputs. Our CoT block is appealing in the view that it can readily replace each $3\times3$ convolution in ResNet architectures, yielding a Transformer-style backbone named as Contextual Transformer Networks (CoTNet). Through extensive experiments over a wide range of applications (e.g., image recognition, object detection and instance segmentation), we validate the superiority of CoTNet as a stronger backbone. Source code is available at \url{https://github.com/JDAI-CV/CoTNet}.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification ImageNet SE-CoTNetD-50 Top 1 Accuracy 81.6% # 562
Number of params 23.1M # 570
GFLOPs 4.1 # 196
Image Classification ImageNet SE-CoTNetD-152 Top 1 Accuracy 84.6% # 284
Number of params 55.8M # 740
GFLOPs 26.5 # 384
Image Classification ImageNet SE-CoTNetD-101 Top 1 Accuracy 83.2% # 407
Number of params 40.9M # 679
GFLOPs 8.5 # 278

Methods