Completed
- From Convolution to Self-Attention for Images
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Axial-DeepLab - Stand-Alone Axial-Attention for Panoptic Segmentation
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro & Overview
- 2 - This Paper's Contributions
- 3 - From Convolution to Self-Attention for Images
- 4 - Learned Positional Embeddings
- 5 - Propagating Positional Embeddings through Layers
- 6 - Traditional vs Position-Augmented Attention
- 7 - Axial Attention
- 8 - Replacing Convolutions in ResNet
- 9 - Experimental Results & Examples
