Sharing Key Semantics in Transformer Makes Efficient Image Restoration

• URL: http://arxiv.org/abs/2405.20008v1
• Date: Thu, 30 May 2024 12:45:34 GMT
• Title: Sharing Key Semantics in Transformer Makes Efficient Image Restoration
• Authors: Bin Ren, Yawei Li, Jingyun Liang, Rakesh Ranjan, Mengyuan Liu, Rita Cucchiara, Luc Van Gool, Ming-Hsuan Yang, Nicu Sebe,
• Abstract summary: Self-attention mechanism, a cornerstone of Vision Transformers (ViTs) tends to encompass all global cues, even those from semantically unrelated objects or regions. We propose boosting Image Restoration's performance by sharing the key semantics via Transformer for IR (i.e., SemanIR) in this paper.
• Score: 148.22790334216117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image Restoration (IR), a classic low-level vision task, has witnessed significant advancements through deep models that effectively model global information. Notably, the Vision Transformers (ViTs) emergence has further propelled these advancements. When computing, the self-attention mechanism, a cornerstone of ViTs, tends to encompass all global cues, even those from semantically unrelated objects or regions. This inclusivity introduces computational inefficiencies, particularly noticeable with high input resolution, as it requires processing irrelevant information, thereby impeding efficiency. Additionally, for IR, it is commonly noted that small segments of a degraded image, particularly those closely aligned semantically, provide particularly relevant information to aid in the restoration process, as they contribute essential contextual cues crucial for accurate reconstruction. To address these challenges, we propose boosting IR's performance by sharing the key semantics via Transformer for IR (i.e., SemanIR) in this paper. Specifically, SemanIR initially constructs a sparse yet comprehensive key-semantic dictionary within each transformer stage by establishing essential semantic connections for every degraded patch. Subsequently, this dictionary is shared across all subsequent transformer blocks within the same stage. This strategy optimizes attention calculation within each block by focusing exclusively on semantically related components stored in the key-semantic dictionary. As a result, attention calculation achieves linear computational complexity within each window. Extensive experiments across 6 IR tasks confirm the proposed SemanIR's state-of-the-art performance, quantitatively and qualitatively showcasing advancements.

Related papers

• ContextFormer: Redefining Efficiency in Semantic Segmentation [46.06496660333768]
  Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers (ViTs) excel in global context capture but are hindered by high computational demands. We propose ContextFormer, a hybrid framework leveraging the strengths of CNNs and ViTs in the bottleneck to balance efficiency, accuracy, and robustness for real-time semantic segmentation.
  arXiv  Detail & Related papers  (2025-01-31T16:11:04Z)
• DAPE V2: Process Attention Score as Feature Map for Length Extrapolation [63.87956583202729]
  We conceptualize attention as a feature map and apply the convolution operator to mimic the processing methods in computer vision. The novel insight, which can be adapted to various attention-related models, reveals that the current Transformer architecture has the potential for further evolution.
  arXiv  Detail & Related papers  (2024-10-07T07:21:49Z)
• Semantic-aware Representation Learning for Homography Estimation [28.70450397793246]
  We propose SRMatcher, a detector-free feature matching method, which encourages the network to learn integrated semantic feature representation. By reducing errors stemming from semantic inconsistencies in matching pairs, our proposed SRMatcher is able to deliver more accurate and realistic outcomes.
  arXiv  Detail & Related papers  (2024-07-18T08:36:28Z)
• You Only Need Less Attention at Each Stage in Vision Transformers [19.660385306028047]
  Vision Transformers (ViTs) capture the global information of images through self-attention modules. We propose the Less-Attention Vision Transformer (LaViT), which computes only a few attention operations at each stage. Our architecture demonstrates exceptional performance across various vision tasks including classification, detection and segmentation.
  arXiv  Detail & Related papers  (2024-06-01T12:49:16Z)
• Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition [48.84506301960988]
  Cued Speech (CS) is a pure visual coding method used by hearing-impaired people. automatic CS recognition (ACSR) seeks to transcribe visual cues of speech into text.
  arXiv  Detail & Related papers  (2024-01-31T05:20:29Z)
• RFR-WWANet: Weighted Window Attention-Based Recovery Feature Resolution Network for Unsupervised Image Registration [7.446209993071451]
  The Swin transformer has attracted attention in medical image analysis due to its computational efficiency and long-range modeling capability. The registration models based on transformers combine multiple voxels into a single semantic token. This merging process limits the transformers to model and generate coarse-grained spatial information. We propose Recovery Feature Resolution Network (RFRNet), which allows the transformer to contribute fine-grained spatial information.
  arXiv  Detail & Related papers  (2023-05-07T09:57:29Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• ClusTR: Exploring Efficient Self-attention via Clustering for Vision Transformers [70.76313507550684]
  We propose a content-based sparse attention method, as an alternative to dense self-attention. Specifically, we cluster and then aggregate key and value tokens, as a content-based method of reducing the total token count. The resulting clustered-token sequence retains the semantic diversity of the original signal, but can be processed at a lower computational cost.
  arXiv  Detail & Related papers  (2022-08-28T04:18:27Z)
• Rethinking Query-Key Pairwise Interactions in Vision Transformers [5.141895475956681]
  We propose key-only attention, which excludes query-key pairwise interactions and uses a compute-efficient saliency-gate to obtain attention weights. We develop a new self-attention model family, LinGlos, which reach state-of-the-art accuracies on the parameter-limited setting of ImageNet classification benchmark.
  arXiv  Detail & Related papers  (2022-07-01T03:36:49Z)
• Rethinking Global Context in Crowd Counting [70.54184500538338]
  A pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token to the input sequence, to facilitate information exchange with tokens corresponding to image patches.
  arXiv  Detail & Related papers  (2021-05-23T12:44:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.