PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

Overview

Image Super-Resolution with Non-Local Sparse Attention

This repository is for NLSN introduced in the following paper "Image Super-Resolution with Non-Local Sparse Attention", CVPR2021, [Link]

The code is built on EDSR (PyTorch) and test on Ubuntu 18.04 environment (Python3.6, PyTorch >= 1.1.0) with V100 GPUs.

Contents

  1. Introduction
  2. Train
  3. Test
  4. Citation
  5. Acknowledgements

Introduction

Both Non-Local (NL) operation and sparse representa-tion are crucial for Single Image Super-Resolution (SISR).In this paper, we investigate their combinations and proposea novel Non-Local Sparse Attention (NLSA) with dynamicsparse attention pattern. NLSA is designed to retain long-range modeling capability from NL operation while enjoying robustness and high-efficiency of sparse representation.Specifically, NLSA rectifies non-local attention with spherical locality sensitive hashing (LSH) that partitions the input space into hash buckets of related features. For everyquery signal, NLSA assigns a bucket to it and only computes attention within the bucket. The resulting sparse attention prevents the model from attending to locations thatare noisy and less-informative, while reducing the computa-tional cost from quadratic to asymptotic linear with respectto the spatial size. Extensive experiments validate the effectiveness and efficiency of NLSA. With a few non-local sparseattention modules, our architecture, called non-local sparsenetwork (NLSN), reaches state-of-the-art performance forSISR quantitatively and qualitatively.

Non-Local Sparse Attention

Non-Local Sparse Attention.

NLSN

Non-Local Sparse Network.

Train

Prepare training data

  1. Download DIV2K training data (800 training + 100 validtion images) from DIV2K dataset or SNU_CVLab.

  2. Specify '--dir_data' based on the HR and LR images path.

For more informaiton, please refer to EDSR(PyTorch).

Begin to train

  1. (optional) Download pretrained models for our paper.

    Pre-trained models can be downloaded from Google Drive

  2. Cd to 'src', run the following script to train models.

    Example command is in the file 'demo.sh'.

    # Example X2 SR
    python main.py --dir_data ../../ --n_GPUs 4 --rgb_range 1 --chunk_size 144 --n_hashes 4 --save_models --lr 1e-4 --decay 200-400-600-800 --epochs 1000 --chop --save_results --n_resblocks 32 --n_feats 256 --res_scale 0.1 --batch_size 16 --model NLSN --scale 2 --patch_size 96 --save NLSN_x2 --data_train DIV2K
    

Test

Quick start

  1. Download benchmark datasets from SNU_CVLab

  2. (optional) Download pretrained models for our paper.

    All the models can be downloaded from Google Drive

  3. Cd to 'src', run the following scripts.

    Example command is in the file 'demo.sh'.

    # No self-ensemble: NLSN
    # Example X2 SR
    python main.py --dir_data ../../ --model NLSN  --chunk_size 144 --data_test Set5+Set14+B100+Urban100 --n_hashes 4 --chop --save_results --rgb_range 1 --data_range 801-900 --scale 2 --n_feats 256 --n_resblocks 32 --res_scale 0.1  --pre_train model_x2.pt --test_only

Citation

If you find the code helpful in your resarch or work, please cite the following papers.

@InProceedings{Mei_2021_CVPR,
    author    = {Mei, Yiqun and Fan, Yuchen and Zhou, Yuqian},
    title     = {Image Super-Resolution With Non-Local Sparse Attention},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {3517-3526}
}
@InProceedings{Lim_2017_CVPR_Workshops,
  author = {Lim, Bee and Son, Sanghyun and Kim, Heewon and Nah, Seungjun and Lee, Kyoung Mu},
  title = {Enhanced Deep Residual Networks for Single Image Super-Resolution},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  month = {July},
  year = {2017}
}

Acknowledgements

This code is built on EDSR (PyTorch) and reformer-pytorch. We thank the authors for sharing their codes.

Owner
Mei Yiqun, Previously @ UIUC
Code for the SIGIR 2022 paper "Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion"

MKGFormer Code for the SIGIR 2022 paper "Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion" Model Architecture Illu

ZJUNLP 68 Dec 28, 2022
Differentiable architecture search for convolutional and recurrent networks

Differentiable Architecture Search Code accompanying the paper DARTS: Differentiable Architecture Search Hanxiao Liu, Karen Simonyan, Yiming Yang. arX

Hanxiao Liu 3.7k Jan 09, 2023
Prompts - Read a textfile of prompts and import into anki via ankiconnect

prompts read a textfile of prompts and import into anki via ankiconnect Usage In

Alexander Cobleigh 2 Jul 28, 2022
Semantic Edge Detection with Diverse Deep Supervision

Semantic Edge Detection with Diverse Deep Supervision This repository contains the code for our IJCV paper: "Semantic Edge Detection with Diverse Deep

Yun Liu 12 Dec 31, 2022
MLPs for Vision and Langauge Modeling (Coming Soon)

MLP Architectures for Vision-and-Language Modeling: An Empirical Study MLP Architectures for Vision-and-Language Modeling: An Empirical Study (Code wi

Yixin Nie 27 May 09, 2022
Roadmap to becoming a machine learning engineer in 2020

Roadmap to becoming a machine learning engineer in 2020, inspired by web-developer-roadmap.

Chris Hoyean Song 1.7k Dec 29, 2022
Prometheus exporter for Cisco Unified Computing System (UCS) Manager

prometheus-ucs-exporter Overview Use metrics from the UCS API to export relevant metrics to Prometheus This repository is a fork of Drew Stinnett's or

Marshall Wace 6 Nov 07, 2022
Python library for computer vision labeling tasks. The core functionality is to translate bounding box annotations between different formats-for example, from coco to yolo.

PyLabel pip install pylabel PyLabel is a Python package to help you prepare image datasets for computer vision models including PyTorch and YOLOv5. I

PyLabel Project 176 Jan 01, 2023
Tensorflow implementation of the paper "HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences", CVPR 2021.

HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences Tensorflow implementation of the paper "HumanGPS: Geodesic PreServing Feature fo

Google Interns 50 Dec 21, 2022
Official repository for the paper "Self-Supervised Models are Continual Learners" (CVPR 2022)

Self-Supervised Models are Continual Learners This is the official repository for the paper: Self-Supervised Models are Continual Learners Enrico Fini

Enrico Fini 73 Dec 18, 2022
🔮 Execution time predictions for deep neural network training iterations across different GPUs.

Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training Habitat is a tool that predicts a deep neural network's

Geoffrey Yu 44 Dec 27, 2022
QA-GNN: Question Answering using Language Models and Knowledge Graphs

QA-GNN: Question Answering using Language Models and Knowledge Graphs This repo provides the source code & data of our paper: QA-GNN: Reasoning with L

Michihiro Yasunaga 434 Jan 04, 2023
A Temporal Extension Library for PyTorch Geometric

Documentation | External Resources | Datasets PyTorch Geometric Temporal is a temporal (dynamic) extension library for PyTorch Geometric. The library

Benedek Rozemberczki 1.9k Jan 07, 2023
DeLag: Detecting Latency Degradation Patterns in Service-based Systems

DeLag: Detecting Latency Degradation Patterns in Service-based Systems Replication package of the work "DeLag: Detecting Latency Degradation Patterns

SEALABQualityGroup @ University of L'Aquila 2 Mar 24, 2022
An ever-growing playground of notebooks showcasing CLIP's impressive zero-shot capabilities.

Playground for CLIP-like models Demo Colab Link GradCAM Visualization Naive Zero-shot Detection Smarter Zero-shot Detection Captcha Solver Changelog 2

Kevin Zakka 101 Dec 30, 2022
Cervix ROI Segmentation Using U-NET

Cervix ROI Segmentation Using U-NET Overview This code illustrate how to segment the ROI in cervical images using U-NET. The ROI here meant to include

Scotty Kwok 35 Sep 14, 2022
Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.

semantic-segmentation-tensorflow This is a Tensorflow implementation of semantic segmentation models on MIT ADE20K scene parsing dataset and Cityscape

HsuanKung Yang 83 Oct 13, 2022
Library for fast text representation and classification.

fastText fastText is a library for efficient learning of word representations and sentence classification. Table of contents Resources Models Suppleme

Facebook Research 24.1k Jan 01, 2023
torchbearer: A model fitting library for PyTorch

Note: We're moving to PyTorch Lightning! Read about the move here. From the end of February, torchbearer will no longer be actively maintained. We'll

632 Dec 13, 2022