Transformers have shown great potential in various computer vision tasks owing to their strong capability in modeling long-range dependency using the self-attention mechanism. Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance. Alternatively, they require large-scale training data and longer training schedules to learn the IB implicitly. In this paper, we propose a novel Vision Transformer Advanced by Exploring intrinsic IB from convolutions, ie, ViTAE. Technically, ViTAE has several spatial pyramid reduction modules to downsample and embed the input image into tokens with rich multi-scale context by using multiple convolutions with different dilation rates. In this way, it acquires an intrinsic scale invariance IB and is able to learn robust feature representation for objects at various scales. Moreover, in each transformer layer, ViTAE has a convolution block in parallel to the multi-head self-attention module, whose features are fused and fed into the feed-forward network. Consequently, it has the intrinsic locality IB and is able to learn local features and global dependencies collaboratively. Experiments on ImageNet as well as downstream tasks prove the superiority of ViTAE over the baseline transformer and concurrent works. Source code and pretrained models will be available at GitHub.
翻译:各种计算机视觉任务中,变异器显示出巨大的潜力,因为其利用自我注意机制进行远距离依赖模型模型模型的强大能力。然而,视觉变异器将图像作为视觉象征的1D序列处理,在模拟当地视觉结构和处理规模差异方面缺乏内在的感应偏差(IB),或者,它们需要大规模培训数据和较长的培训时间表来隐含地学习IB。在本文件中,我们提出一个新的视野变异变异变异器,通过探索多头自留模块的内在 IB 推进。在技术上,VitAE拥有几个空间金字塔减缩模块,通过使用具有不同变异率的多重变异变(IB ) 将输入图像嵌入丰富多尺度背景的符号中。因此,它获得了内在变异性IB 的内在规模,能够学习不同尺度天体的特征。此外,VITAE在每一个变异层中都有一个与多头自留模块平行的相变变形块块块,其特征被连接并被反馈到进向上网络。因此,它拥有内在的IB和GiLOFS的软化模型,作为全球级模型的基础,能够学习。