RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging

• URL: http://arxiv.org/abs/2302.02519v1
• Date: Mon, 6 Feb 2023 01:13:13 GMT
• Title: RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging
• Authors: Shiyun Zhou, Tingfa Xu, Shaocong Dong and Jianan Li
• Abstract summary: We introduce a regional dynamic way of using Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) to exploit regional characteristics. We then unfold the process into a hierarchical dynamic deep network, dubbed RDFNet. Our proposed regional dynamic architecture can also learn appropriate shrinkage scale in a pixel-wise manner.
• Score: 11.627511305913476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep convolutional neural networks have recently shown promising results in compressive spectral reconstruction. Previous methods, however, usually adopt a single mapping function for sparse representation. Considering that different regions have distinct characteristics, it is desirable to apply various mapping functions to adjust different regions' transformations dynamically. With this in mind, we first introduce a regional dynamic way of using Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) to exploit regional characteristics and derive dynamic sparse representations. Then, we propose to unfold the process into a hierarchical dynamic deep network, dubbed RDFNet. The network comprises multiple regional dynamic blocks and corresponding pixel-wise adaptive soft-thresholding modules, respectively in charge of region-based dynamic mapping and pixel-wise soft-thresholding selection. The regional dynamic block guides the network to adjust the transformation domain for different regions. Equipped with the adaptive soft-thresholding, our proposed regional dynamic architecture can also learn appropriate shrinkage scale in a pixel-wise manner. Extensive experiments on both simulated and real data demonstrate that our method outperforms prior state-of-the-arts.

Related papers

• Adaptive Mesh-Quantization for Neural PDE Solvers [51.26961483962011]
  Graph Neural Networks can handle the irregular meshes required for complex geometries and boundary conditions, but still apply uniform computational effort across all nodes.<n>We propose Adaptive Mesh Quantization: spatially adaptive quantization across mesh node, edge, and cluster features, dynamically adjusting the bit-width used by a quantized model.<n>We demonstrate our framework's effectiveness by integrating it with two state-of-the-art models, MP-PDE and GraphViT, to evaluate performance across multiple tasks.
  arXiv  Detail & Related papers  (2025-11-23T14:47:24Z)
• Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition [55.52723195212868]
  GaitRDAE is a framework that automatically searches for motion regions, assigns adaptive temporal scales and applies corresponding attention.<n> Experimental results show that GaitRDAE achieves state-of-the-art performance on several benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-18T15:36:08Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• Improving regional weather forecasts with neural interpolation [0.0]
  We design a neural operator to improve the boundary data for regional weather models.<n>In particular, we expose a methodology for approaching the problem through the study of a simplified model.<n>Our approach will exploit a combination of techniques from image super-resolution with convolutional neural networks (CNNs) and residual networks.
  arXiv  Detail & Related papers  (2025-05-17T15:05:09Z)
• Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification [12.168520751389622]
  Deep neural networks face several challenges in hyperspectral image classification. These include complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features. This paper proposes a Spatial-Geometry Enhanced 3D Dynamic Snake Network (SG-DSCNet) based on an improved 3D-DenseNet model.
  arXiv  Detail & Related papers  (2025-04-06T12:21:39Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• 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)
• Hierarchical Dynamic Image Harmonization [15.886047676987316]
  We propose a hierarchical dynamic network (HDNet) to adapt features from local to global view for better feature transformation in efficient image harmonization. The proposed HDNet significantly reduces the total model parameters by more than 80% compared to previous methods. Notably, the HDNet achieves a 4% improvement in PSNR and a 19% reduction in MSE compared to the prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-16T03:15:19Z)
• Semantic Segmentation by Early Region Proxy [53.594035639400616]
  We present a novel and efficient modeling that starts from interpreting the image as a tessellation of learnable regions. To model region-wise context, we exploit Transformer to encode regions in a sequence-to-sequence manner. Semantic segmentation is now carried out as per-region prediction on top of the encoded region embeddings.
  arXiv  Detail & Related papers  (2022-03-26T10:48:32Z)
• Domain Adaptive Semantic Segmentation with Regional Contrastive Consistency Regularization [19.279884432843822]
  We propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation. Our core idea is to pull the similar regional features extracted from the same location of different images to be closer, and meanwhile push the features from the different locations of the two images to be separated.
  arXiv  Detail & Related papers  (2021-10-11T11:45:00Z)
• Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation [27.624291416260185]
  We propose a Dynamic Dual Sampling Module (DDSM) to conduct dynamic affinity modeling and propagate semantic context to local details. Experiment results on both City and Camvid datasets validate the effectiveness and efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2021-05-25T04:25:47Z)
• Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition [7.475025465262353]
  We propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition. We replace the fixed Inception modules with the automatically rebuilt structure through the network via Neural Architecture Search (NAS) It enables the network to capture different levels of feature representations at different layers more adaptively.
  arXiv  Detail & Related papers  (2021-02-10T09:36:00Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)
• Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification [58.20132466198622]
  We propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly.
  arXiv  Detail & Related papers  (2020-03-29T15:01:05Z)
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction [41.62169556793355]
  Deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition. It is not clear how to choose a suitable network architecture to balance the trade-off between network complexity and performance. This paper proposes a systematic geometric approach using bootstrapping and subnetwork aggregation to increase the expressivity of the underlying neural network.
  arXiv  Detail & Related papers  (2020-03-17T14:18:37Z)

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.