VIT
[toc] Vision Transformer () 文章标题：An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 作者：Alexey Dosovitskiy; Lucas Beyer, Alexander …
TECHNICAL JOURNAL
AI、Tracing、Profiling 与系统工程的长期记录
Archive
64
篇文章
Latest
2026-04-01
最近更新
Latest writing
更多文章
ALBEF
文章标题：Align before Fuse: Vision and Language Representation Learning with Momentum Distillation 作者：Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, …
CLIP
文章标题：Learning Transferable Visual Models From Natural Language Supervision 作者：Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini …
VILT
文章标题：ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision 作者：Wonjae Kim, Bokyung Son, Ildoo Kim 发表时间：(ICML 2021) offical code 第一个摆脱了目 …
BYOL
SwAV 文章标题：Unsupervised Learning of Visual Features by Contrasting Cluster Assignments 作者：Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr …
InstDisc
文章标题：Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination 作者：Zhirong Wu, Yuanjun Xiong, Stella Yu, Dahua Lin 发表时间：(CVPR 2018) 这篇论文提出了个 …
Moco
MoCo 文章标题：Momentum Contrast for Unsupervised Visual Representation Learning 作者：Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick 发表时间：(CVPR 2020) …
SimCLR
-V1 文章标题：A Simple Framework for Contrastive Learning of Visual Representations 作者：Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton 发表时间：(ICML 2020) …
Branch Channel Attention
different branches SKNet 文章标题：Selective Kernel Networks 作者：Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang 发表时间：(CVPR 2019) Official Code SK_module 用multiple scale …