每日Paper进步屋
Vision Transformer Vision Transformer
2022-10-25 更新UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery DetectionAu
Vision Transformer Vision Transformer
2022-10-24 更新CLIP also Understands Text: Prompting CLIP for Phrase UnderstandingAuthors:An Yan, Jiacheng Li, Wanrong Zhu
Vision Transformer Vision Transformer
2022-10-21 更新Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image RetrievalAuthors:Abhra Chaudhuri, Mas
Vision Transformer Vision Transformer
2022-10-19 更新VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-TrainingAuthors:Z
Vision Transformer Vision Transformer
2022-10-18 更新Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak LabelsAuthors
Vision Transformer Vision Transformer
2022-10-17 更新Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?Authors:Van-Anh Nguyen, Khanh
Vision Transformer Vision Transformer
2022-10-15 更新Token-Label Alignment for Vision TransformersAuthors:Han Xiao, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu
Vision Transformer Vision Transformer
2022-10-12 更新Lightweight Transformer Backbone for Medical Object DetectionAuthors:Yifan Zhang, Haoyu Dong, Nicholas Konz
Vision Transformer Vision Transformer
2022-10-11 更新PatchDropout: Economizing Vision Transformers Using Patch DropoutAuthors:Yue Liu, Christos Matsoukas, Fredr
15 / 28