Search Results for author:
Found 2 papers, 1 papers with code
MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition
We develop a simple but effective module to explore the full potential of transformers for visual representation by learning fine-grained and coarse-grained features at a token level and dynamically fusing them.
Context Autoencoder for Self-Supervised Representation Learning
The pretraining tasks include two tasks: masked representation prediction - predict the representations for the masked patches, and masked patch reconstruction - reconstruct the masked patches.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
