Adaptive Cross-Layer Attention for Image Restoration

• URL: http://arxiv.org/abs/2203.03619v3
• Date: Tue, 18 Apr 2023 21:41:11 GMT
• Title: Adaptive Cross-Layer Attention for Image Restoration
• Abstract summary: Non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. We propose a novel Adaptive Cross-Layer Attention (ACLA) module. Two adaptive designs are proposed for ACLA: (1) adaptively selecting the keys for non-local attention at each layer; (2) automatically searching for the insertion locations for ACLA modules.
• Score: 10.795382525098917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Non-local attention module has been proven to be crucial for image restoration. Conventional non-local attention processes features of each layer separately, so it risks missing correlation between features among different layers. To address this problem, we aim to design attention modules that aggregate information from different layers. Instead of finding correlated key pixels within the same layer, each query pixel is encouraged to attend to key pixels at multiple previous layers of the network. In order to efficiently embed such attention design into neural network backbones, we propose a novel Adaptive Cross-Layer Attention (ACLA) module. Two adaptive designs are proposed for ACLA: (1) adaptively selecting the keys for non-local attention at each layer; (2) automatically searching for the insertion locations for ACLA modules. By these two adaptive designs, ACLA dynamically selects a flexible number of keys to be aggregated for non-local attention at previous layer while maintaining a compact neural network with compelling performance. Extensive experiments on image restoration tasks, including single image super-resolution, image denoising, image demosaicing, and image compression artifacts reduction, validate the effectiveness and efficiency of ACLA. The code of ACLA is available at \url{https://github.com/SDL-ASU/ACLA}.

Related papers

• Enhancing Layer Interaction Using Key-Correlated Layer Attention [12.760214212097795]
  Key-Correlated Layer Attention (KCLA) is inspired by our observation that Key representations in layer attention exhibit high cosine similarity.<n>KCLA achieves linear computational complexity while preserving dynamic information updates.<n>It delivers good performance across diverse tasks, including image recognition, object detection, and medical image segmentation.
  arXiv  Detail & Related papers  (2026-06-24T13:54:52Z)
• IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE [2.5282283486446753]
  Image-adaptive contrast limited adaptive histogram equalization (IA- CLAHE)<n> Conventional CLAHE is widely used to boost the performance of various computer vision tasks.<n>IA- CLAHE addresses this limitation by adaptively estimating tile-wise clip limits from the input image.
  arXiv  Detail & Related papers  (2026-04-17T12:33:45Z)
• OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval [59.377821673653436]
  Composed Image Retrieval (CIR) is capable of expressing users' intricate retrieval requirements flexibly.<n>CIR remains in its nascent stages due to two limitations: 1) inhomogeneity between dominant and noisy portions in visual data is ignored, leading to query feature degradation.<n>This work presents a focus mapping-based feature extractor, which consists of two modules: dominant portion segmentation and dual focus mapping.
  arXiv  Detail & Related papers  (2025-07-08T03:27:46Z)
• SCAPE: A Simple and Strong Category-Agnostic Pose Estimator [6.705257644513057]
  Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category given few exemplars in an in-context manner. We introduce two key modules: a global keypoint feature perceptor to inject global semantic information into support keypoints, and a keypoint attention refiner to enhance inter-node correlation between keypoints. SCAPE outperforms prior arts by 2.2 and 1.3 PCK under 1-shot and 5-shot settings with faster inference speed and lighter model capacity.
  arXiv  Detail & Related papers  (2024-07-18T13:02:57Z)
• Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model [18.138932199576917]
  Current state-of-the-art diffusion models employ U-Net architectures containing convolutional and (qkv) self-attention layers. We show that simply adding LoRA conditioning to the attention layers without changing or tuning the other parts of the U-Net architecture improves the image generation quality.
  arXiv  Detail & Related papers  (2024-05-07T02:45:28Z)
• Efficient and Explicit Modelling of Image Hierarchies for Image Restoration [120.35246456398738]
  We propose a mechanism to efficiently and explicitly model image hierarchies in the global, regional, and local range for image restoration. Inspired by that, we propose the anchored stripe self-attention which achieves a good balance between the space and time complexity of self-attention. Then we propose a new network architecture dubbed GRL to explicitly model image hierarchies in the Global, Regional, and Local range.
  arXiv  Detail & Related papers  (2023-03-01T18:59:29Z)
• Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification [61.411869453639845]
  We introduce a bi-reconstruction mechanism that can simultaneously accommodate for inter-class and intra-class variations. This design effectively helps the model to explore more subtle and discriminative features. Experimental results on three widely used fine-grained image classification datasets consistently show considerable improvements.
  arXiv  Detail & Related papers  (2022-11-30T16:55:14Z)
• Data Augmentation Vision Transformer for Fine-grained Image Classification [1.6211899643913996]
  We propose a data augmentation vision transformer (DAVT) based on data augmentation. We also propose a hierarchical attention selection (HAS) method, which improves the ability of discriminative markers between levels of learning. Experimental results show that the accuracy of this method on the two general datasets, CUB-200-2011, and Stanford Dogs, is better than the existing mainstream methods.
  arXiv  Detail & Related papers  (2022-11-23T11:34:11Z)
• Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation [72.33139350241044]
  Weakly Supervised Semantic COCO (WSSS) based on image-level labels has attracted much attention due to low annotation costs. We propose a Self-supervised Image-specific Prototype Exploration (SIPE) that consists of an Image-specific Prototype Exploration (IPE) and a General-Specific Consistency (GSC) loss. Our SIPE achieves new state-of-the-art performance using only image-level labels.
  arXiv  Detail & Related papers  (2022-03-06T09:01:03Z)
• Progressive Co-Attention Network for Fine-grained Visual Classification [20.838908090777885]
  Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. Most existing methods only take individual image as input. We propose an effective method called progressive co-attention network (PCA-Net) to tackle this problem.
  arXiv  Detail & Related papers  (2021-01-21T10:19:02Z)
• Single Image Super-Resolution via a Holistic Attention Network [87.42409213909269]
  We propose a new holistic attention network (HAN) to model the holistic interdependencies among layers, channels, and positions. The proposed HAN adaptively emphasizes hierarchical features by considering correlations among layers. Experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.
  arXiv  Detail & Related papers  (2020-08-20T04:13:15Z)
• Learning to Compose Hypercolumns for Visual Correspondence [57.93635236871264]
  We introduce a novel approach to visual correspondence that dynamically composes effective features by leveraging relevant layers conditioned on the images to match. The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional neural network.
  arXiv  Detail & Related papers  (2020-07-21T04:03:22Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)

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.