Global Learnable Attention For Single Image Super-resolution

Abstract

Self-similarity is valuable to the exploration of non-local textures in single image super-resolution (SISR). Researchers usually assume that the importance of non-local textures is positively related to their similarity scores. In this paper, we surprisingly found that when repairing severely damaged query textures, some non-local textures with low-similarity which are closer to the target can provide more accurate and richer details than the high-similarity ones. In these cases, low-similarity does not mean inferior but is usually caused by different scales or orientations. 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. The proposed GLA can explore non-local textures with low-similarity but more accurate details to repair severely damaged textures. Furthermore, we propose to adopt Super-Bit Locality-Sen

Stats

• citations36
• S2 citations—
• github stars0
• HF likes0
• heat score11.76
• arxiv keysu2022global

Related papers

• Learning Super-features For Image Retrieval (2022)4.31
• Self-supervising Fine-grained Region Similarities For Large-scale Image Localization (2020)15.85
• All The Attention You Need: Global-local, Spatial-channel Attention For Image Retrieval (2021)13.97
• Visual Similarity Attention (2019)0.00
• Lesion Search With Self-supervised Learning (2023)0.00
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
• Domain-invariant Similarity Activation Map Contrastive Learning For Retrieval-based Long-term Visual Localization (2020)13.72
• Global Features Are All You Need For Image Retrieval And Reranking (2023)17.53