Résumé: Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance, which is instead learned implicitly from large-scale training data with longer training schedules. In this paper, we leverage the two IBs and propose the ViTAE transformer, which utilizes a reduction cell for multi-scale feature and a normal cell for locality. The two kinds of cells are stacked in both isotropic and multi-stage manners to formulate two families of ViTAE models, i.e., the vanilla ViTAE and ViTAEv2. Experiments on the ImageNet dataset as well as downstream tasks on the MS COCO, ADE20K, and AP10K datasets validate the superiority of our models over the baseline and representative models. Besides, we scale up our ViTAE model to 644 M parameters and obtain the state-of-the-art classification performance, i.e., 88.5% Top-1 classification accuracy on ImageNet validation set and the best 91.2% Top-1 classification accuracy on ImageNet Real validation set, without using extra private data. It demonstrates that the introduced inductive bias still helps when the model size becomes large. The source code and pretrained models are publicly available atcode.

Langue: Anglais