paper-with-me

Papers

Adaptive Step-size Perception Unfolding Network with Non-local Hybrid Attention for Hyperspectral Image Reconstruction

2024-07-04 · Yanan Yang, Like Xin

Deep unfolding methods and transformer architecture have recently shown promising results in hyperspectral image (HSI) reconstruction. However, there still exist two issues: (1) in the data subproblem, most methods represents the stepsize utilizing a learnable parameter. Nevertheless, for different spectral channel, error between features and ground truth is unequal. (2) Transformer struggles to balance receptive field size with pixel-wise detail information. To overcome the aforementioned drawbacks, We proposed an adaptive step-size perception unfolding network (ASPUN), a deep unfolding network based on FISTA algorithm, which uses an adaptive step-size perception module to estimate the update step-size of each spectral channel. In addition, we design a Non-local Hybrid Attention Transformer(NHAT) module for fully leveraging the receptive field advantage of transformer. By plugging the NLHA into the Non-local Information Aggregation (NLIA) module, the unfolding network can achieve better reconstruction results. Experimental results show that our ASPUN is superior to the existing SOTA algorithms and achieves the best performance.

📄 PDF Abstract BibTeX arXiv:2407.04024

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Deep Unfolding Network for Image Compressed Sensing by Content-adaptive Gradient Updating and Deformation-invariant Non-local Modeling

2023-10-16 · Wenxue Cui, Xiaopeng Fan, Jian Zhang, Debin Zhao

Inspired by certain optimization solvers, the deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS). However, there still exist the following two issues: 1) In existi…

compressed sensingImage Compressed Sensing

Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction

2023-08-21 · ICCV 2023 1 · Miaoyu Li, Ying Fu, Ji Liu, Yulun Zhang

Hyperspectral Image (HSI) reconstruction has made gratifying progress with the deep unfolding framework by formulating the problem into a data module and a prior module. Nevertheless, existing methods still face the prob…

Image Reconstruction

Deep Unfolding with Kernel-based Quantization in MIMO Detection

2025-05-19 · Zeyi Ren, Jingreng Lei, Yichen Jin, Ermo Hua 외

The development of edge computing places critical demands on energy-efficient model deployment for multiple-input multiple-output (MIMO) detection tasks. Deploying deep unfolding models such as PGD-Nets and ADMM-Nets int…

Density EstimationEdge-computingQuantization

Dual-Path Hyperprior Informed Deep Unfolding Network for Image Compressive Sensing

2026-05-10 · Tianyi Lu, Wenxue Cui, Shaohui Liu arxiv

Recent Deep Unfolding Networks (DUNs) have significantly advanced Compressive Sensing (CS) by integrating iterative optimization with deep networks. However, existing DUNs still suffer from two challenges: 1) Reliance on…

Compressive Sensing

Sentence Alignment using Unfolding Recursive Autoencoders

2017-08-01 · WS 2017 8 · Jeenu Grover, Pabitra Mitra

In this paper, we propose a novel two step algorithm for sentence alignment in monolingual corpora using Unfolding Recursive Autoencoders. First, we use unfolding recursive auto-encoders (RAE) to learn feature vectors fo…

Information RetrievalMachine TranslationParaphrase IdentificationQuestion Answering+2