Unifying Global-Local Representations in Salient Object Detection with Transformer

Last update: Aug 24, 2022

Related tags

Deep Learning GLSTR

Overview

GLSTR (Global-Local Saliency Transformer)

This is the official implementation of paper "Unifying Global-Local Representations in Salient Object Detection with Transformer" by Sucheng Ren, Qiang Wen, Nanxuan Zhao, Guoqiang Han, Shengfeng He

Prerequisites

The whole training process can be done on eight RTX2080Ti or four RTX3090.

Pytorch 1.6

Datasets

Training Set

We use the training set of DUTS (DUTS-TR) to train our model.

/path/to/DUTS-TR/
   img/
      img1.jpg
   label/
      label1.png

Testing Set

We test our model on the testing set of DUTS, ECSSD, HKU-IS, PASCAL-S, DUT-OMRON, and SOD to test our model.

Training

Download the pretrained transformer backbone on ImageNet.

# input the path to training data and pretrained backbone in train.sh
bash train.sh

Testing

Download the pretrained model from Baidu pan(code: uo0a), Google drive, and put it int ./ckpt/

python test.py

Evaluation

The precomputed saliency maps (DUTS-TE, ECSSD, HKU-IS, PASCAL-S, DUT-OMRON, and SOD) can be found at Baidu pan(code: uo0a), Google drive.

After paper submission, we retrain the model, and the performance is improved. Feel free to use the results of our paper or the precomputed saliency maps.

Contact

If you have any questions, feel free to email Sucheng Ren :) ([email protected])

Citation

Please cite our paper if you think the code and paper are helpful.

@article{ren2021unifying,
  title={Unifying Global-Local Representations in Salient Object Detection with Transformer},
  author={Ren, Sucheng and Wen, Qiang and Zhao, Nanxuan and Han, Guoqiang and He, Shengfeng},
  journal={arXiv preprint arXiv:2108.02759},
  year={2021}
}

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

NLopt is a library for nonlinear local and global optimization, for functions with and without gradient information. It is designed as a simple, unifi

1.4k Dec 25, 2022

Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Self-supervised Graph-level Representation Learning with Local and Global Structure Introduction This project is an implementation of ``Self-supervise

50 Dec 9, 2022

Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

Focal Transformer This is the official implementation of our Focal Transformer -- "Focal Self-attention for Local-Global Interactions in Vision Transf

486 Dec 20, 2022

Decentralized Reinforcment Learning: Global Decision-Making via Local Economic Transactions (ICML 2020)

Decentralized Reinforcement Learning This is the code complementing the paper Decentralized Reinforcment Learning: Global Decision-Making via Local Ec

40 Oct 30, 2022

Pytorch implementation of 'Fingerprint Presentation Attack Detector Using Global-Local Model'

RTK-PAD This is an official pytorch implementation of 'Fingerprint Presentation Attack Detector Using Global-Local Model', which is accepted by IEEE T

6 Aug 1, 2022

Losslandscapetaxonomy - Taxonomizing local versus global structure in neural network loss landscapes

Taxonomizing local versus global structure in neural network loss landscapes Int

8 Dec 30, 2022

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Hybrid-Supervised Object Detection System Object detection system trained by hybrid-supervision/weakly semi-supervision (HSOD/WSSOD): This project is

5 Dec 10, 2022

Yolo object detection - Yolo object detection with python

How to run download required files make build_image make download Docker versio

3 Jan 26, 2022

(IEEE TIP 2021) Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

RDPNet IEEE TIP 2021: Regularized Densely-connected Pyramid Network for Salient Instance Segmentation PyTorch training and testing code are available.

41 Oct 21, 2022

Comments

Can you share ground truth in SOD dataset?

Hello! Can you share ground truth in SOD dataset? It's too hard to me to process SOD dataset. Can you help me? Thanks a lot!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!🙇‍

opened by YoucanBaby 1

Unifying Global-Local Representations in Salient Object Detection with Transformer

Related tags

Overview

GLSTR (Global-Local Saliency Transformer)

Prerequisites

Datasets

Training Set

Testing Set

Training

Testing

Evaluation

Contact

Citation

You might also like...

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Official code for "Focal Self-attention for Local-Global Interactions in Vision Transformers"

Decentralized Reinforcment Learning: Global Decision-Making via Local Economic Transactions (ICML 2020)

Pytorch implementation of 'Fingerprint Presentation Attack Detector Using Global-Local Model'

Losslandscapetaxonomy - Taxonomizing local versus global structure in neural network loss landscapes

Hybrid CenterNet - Hybrid-supervised object detection / Weakly semi-supervised object detection

Yolo object detection - Yolo object detection with python

(IEEE TIP 2021) Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

Comments

Can you share ground truth in SOD dataset?

Owner

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

The official repo of the CVPR 2021 paper Group Collaborative Learning for Co-Salient Object Detection .

Code for ACM MM2021 paper "Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection"

Code for the TIP 2021 Paper "Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss"

Code for the ICME 2021 paper "Exploring Driving-Aware Salient Object Detection via Knowledge Transfer"

Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.

Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)

[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.