Myvideo

Guest

Login

A ConvNet for the 2020s Paper Explained (with animations)

Uploaded By: Myvideo
7 views
0
0 votes
0

Can a ConvNet outperform a Vision Transformer? What kind of modifications do we have to apply to a ConvNet to make it as powerful as a Transformer? Spoiler: it’s not attention. β–Ί SPONSOR: Weights & Biases πŸ‘‰ The official ConvNeXt repo has a W&B integration! Also, W&B built the CIFAR10 training colab linked there: πŸ₯³ ❓ Check out our daily #MachineLearning Quiz Questions: Explained Paper πŸ“œ: Liu, Zhuang, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. β€œA ConvNet for the 2020s.” arXiv preprint arXiv: (2022). πŸ”— Tweet of Lukas Beyer (ViT author): πŸ”— Depthwise convolutions image and explanation:

Share with your friends

Link:

Embed:

Video Size:

Custom size:

x

Add to Playlist:

Favorites
My Playlist
Watch Later