Search Results for author:
Found 2 papers, 1 papers with code
High-Similarity-Pass Attention for Single Image Super-Resolution
Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution.
Global Learnable Attention for Single Image Super-Resolution
Utilizing this finding, we proposed a Global Learnable Attention (GLA) to adaptively modify similarity scores of non-local textures during training instead of only using a fixed similarity scoring function such as the dot product.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
