2022-04-07 更新
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Authors:Qi Han, Zejia Fan, Qi Dai, Lei Sun, Ming-Ming Cheng, Jiaying Liu, Jingdong Wang
Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the attention separately over small local windows. We rephrase local attention as a channel-wise locally-connected layer and analyze it from two network regularization manners, sparse connectivity and weight sharing, as well as weight computation. Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window. Weight sharing: the connection weights for one position are shared across channels or within each group of channels. Dynamic weight: the connection weights are dynamically predicted according to each image instance. We point out that local attention resembles depth-wise convolution and its dynamic version in sparse connectivity. The main difference lies in weight sharing - depth-wise convolution shares connection weights (kernel weights) across spatial positions. We empirically observe that the models based on depth-wise convolution and the dynamic variant with lower computation complexity perform on-par with or sometimes slightly better than Swin Transformer, an instance of Local Vision Transformer, for ImageNet classification, COCO object detection and ADE semantic segmentation. These observations suggest that Local Vision Transformer takes advantage of two regularization forms and dynamic weight to increase the network capacity. Code is available at https://github.com/Atten4Vis/DemystifyLocalViT.
PDF ICLR 2022 Spotlight
论文截图
Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
Authors:Yuxin Fang, Shusheng Yang, Shijie Wang, Yixiao Ge, Ying Shan, Xinggang Wang
We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT can work surprisingly well in the challenging object-level recognition scenario even with random sampled partial observations, e.g., only 25% ~ 50% of the input sequence. (ii) In order to construct multi-scale representations for object detection, a random initialized compact convolutional stem supplants the pre-trained large kernel patchify stem, and its intermediate features can naturally serve as the higher resolution inputs of a feature pyramid without upsampling. While the pre-trained ViT is only regarded as the third-stage of our detector’s backbone instead of the whole feature extractor, resulting in a ConvNet-ViT hybrid architecture. The proposed detector, named MIMDet, enables a MIM pre-trained vanilla ViT to outperform hierarchical Swin Transformer by 2.3 box AP and 2.5 mask AP on COCO, and achieve even better results compared with other adapted vanilla ViT using a more modest fine-tuning recipe while converging 2.8x faster. Code and pre-trained models are available at \url{https://github.com/hustvl/MIMDet}.
PDF Preprint. Work in progress. Code and pre-trained models are available at \url{https://github.com/hustvl/MIMDet}
论文截图