每日Paper进步屋
  文章分类
NeRF 225 Diffusion Models 171 对抗攻击 164 Vision Transformer 250 人脸相关 138 检测/分割/跟踪 290 GAN 277 无监督/半监督/对比学习 234 医学影像/息肉检测分割 39 视频理解 72 I2I Translation 244 医学影像/Breast Ultrasound 19 Anti-Spoofing 45 场景文本检测识别 70 Few-Shot 183 强化学习 92 Open-Set 75 元宇宙/虚拟人 82 Domain Adaptation 169 Speech 108 MMT 17 Face Swapping 11 LLM 46 Human reconstruction 6 NeRF/3DGS 22 图像生成 24 点云相关 11 视频生成 18
Vision Transformer Vision Transformer
2023-04-07 更新Towards an Effective and Efficient Transformer for Rain-by-snow Weather RemovalAuthors:Tao Gao, Yuanbo We
2023-04-07 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-04-04 更新Rethinking Local Perception in Lightweight Vision TransformerAuthors:Qihang Fan, Huaibo Huang, Jiyang Guan,
2023-04-04 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-04-03 更新Rethinking Local Perception in Lightweight Vision TransformerAuthors:Qihang Fan, Huaibo Huang, Jiyang Guan,
2023-04-03 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-31 更新Supervised Masked Knowledge Distillation for Few-Shot TransformersAuthors:Han Lin, Guangxing Han, Jiawei Ma
2023-03-31 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-30 更新TFS-ViT: Token-Level Feature Stylization for Domain GeneralizationAuthors:Mehrdad Noori, Milad Cheraghalikh
2023-03-30 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-29 更新Sector Patch Embedding: An Embedding Module Conforming to The Distortion Pattern of Fisheye ImageAuthors:
2023-03-29 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-27 更新Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete LabelsAuthors:Zixuan Ding
2023-03-27 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-24 更新From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and C
2023-03-24 Vision Transformer
Vision Transformer
Vision Transformer Vision Transformer
2023-03-23 更新MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationAutho
2023-03-23 Vision Transformer
Vision Transformer
8 / 28