ConvNeXt: A ConvNet for the 2020s | Paper Explained
β€οΈ Become The AI Epiphany Patreon β€οΈ
π¨βπ©βπ§βπ¦ Join our Discord community π¨βπ©βπ§βπ¦
In this video I cover the recently published βA ConvNet for the 2020sβ paper. They show that ConvNets are still in the game! - by adding new design ideas and training procedures they outperform vision transformers even in big data regimes and without any attention layers.
Convolutional prior continues to stand the test of time in the field of computer vision.
Note: I also partially cover the Swin transformer paper in case you missed out on that one. :)
β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬β¬
β
Paper:
β
GitH