Unsupervised Foreground Extraction via Deep Region Competition

Related tags

Deep Learning DRC
Overview

Unsupervised Foreground Extraction via Deep Region Competition teaser

[Paper] [Code]

The official code repository for NeurIPS 2021 paper "Unsupervised Foreground Extraction via Deep Region Competition".

Installation

The implementation depends on the following commonly used packages, all of which can be installed via conda.

Package Version
PyTorch ≥ 1.8.1
numpy not specified (we used 1.20.0)
opencv-python 4.5.1.48
pandas 1.2.3

Datasets and Pretrained Models

Datasets and pretrained models are available at: https://drive.google.com/drive/folders/1qItekRJcOYBIcVi4ChrcyzwFVl-lrw23?usp=sharing

Please follow the following commands to obtain the CLEVR6 dataset:

# Download `clevr_with_masks_train.tfrecords` from deepmind gcloud
cd drc_workspace/scripts
wget https://storage.googleapis.com/multi-object-datasets/clevr_with_masks/clevr_with_masks_train.tfrecords
python load_clevr_with_masks.py

This will save the generated dataset in the meta folder.

Training

# Train a foreground extractor with specified checkpoint folder
python main.py --checkpoints <TO_BE_SPECIFIED>

You may specify the value of arguments during training. Please find the available arguments in the config.yml.example file in drc_workspace folder. Note that config.yml.example file provides the training parameters on full CUB dataset. Parameters on other datasets and data splits can be found in the drc_workspace/config_gallery folder.

Note that DATA indicates the dataset to use (CUB, DOG, CAR, CLEVR and TEXTURED). The path to your dataset folder, i.e., ROOT_DIR, needs to be specified before running the script.

Testing

# Evaluate the extractor
python test.py --checkpoints <TO_BE_SPECIFIED>

Citation

@inproceedings{yu2021unsupervised,
  author = {Yu, Peiyu and Xie, Sirui and Ma, Xiaojian and Zhu, Yixin and Wu, Ying Nian and Zhu, Song-Chun},
  title = {Unsupervised Foreground Extraction via Deep Region Competition},
  booktitle = {Proceedings of Advances in Neural Information Processing Systems (NeurIPS)},
  month = {December},
  year = {2021}
}
You might also like...
It's a implement of this paper：Relation extraction via Multi-Level attention CNNs
It's a implement of this paper：Relation extraction via Multi-Level attention CNNs

Relation Classification via Multi-Level Attention CNNs It's a implement of this paper：Relation Classification via Multi-Level Attention CNNs. Training

Aybss 2 Nov 4, 2022
NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

NFT-Price-Prediction-CNN - Using visual feature extraction, prices of NFTs are predicted via CNN (Alexnet and Resnet) architectures.

null 5 Nov 3, 2022
SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022
SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

SafePicking Learning Safe Object Extraction via Object-Level Mapping Kentaro Wad

Kentaro Wada 49 Oct 24, 2022
PyTorch Implementation of Region Similarity Representation Learning (ReSim)
PyTorch Implementation of Region Similarity Representation Learning (ReSim)

ReSim This repository provides the PyTorch implementation of Region Similarity Representation Learning (ReSim) described in this paper: @Article{xiao2

Tete Xiao 74 Jan 3, 2023
Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation
Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation (AAAI 2021) Official pytorch implementation of our paper: Discriminative

Beom 74 Dec 27, 2022
Code for the ICML 2021 paper:
Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT Code for the paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision" Install pip install -r requirements.txt pip

Wonjae Kim 922 Jan 1, 2023
Code for the ICML 2021 paper:
Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT Code for the paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision" Install pip install -r requirements.txt pip

Wonjae Kim 922 Jan 1, 2023
[CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment
[CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment

RADN [CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment [Paper on arXiv] Overview Update [2021/5/7] add codes for W

IIGROUP 53 Dec 28, 2022
Official Implementation and Dataset of
Official Implementation and Dataset of "PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021

Portrait Photo Retouching with PPR10K Paper | Supplementary Material PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask an

null 184 Dec 11, 2022
Comments
  • About original images of dog dataset

    About original images of dog dataset

    Hello, I found in car dataset there are original, cropped and resized images, but in Dog dataset it only has resized images. Could you share the original and cropped images of dog dataset? It would help a lot for data preprocessing! Thanks!

    opened by qrzou 1
  • Missing train_val_test_split.txt file in CUB dataset.

    Missing train_val_test_split.txt file in CUB dataset.

    Hello, I found CubDataset uses train_val_test_split.txt file, but I didn't find it in the CUB zip file you provided. Could you share the file? Thanks!

    opened by qrzou 1
Owner
null
GitHub
FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery (TGRS)

FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery by Ailong Ma, Junjue Wang*, Yanfei Zhon

Kingdrone 43 Jan 5, 2023
[AAAI-2021] Visual Boundary Knowledge Translation for Foreground Segmentation

Trans-Net Code for (Visual Boundary Knowledge Translation for Foreground Segmentation, AAAI2021). [https://ojs.aaai.org/index.php/AAAI/article/view/16

ZJU-VIPA 2 Mar 4, 2022
DETReg: Unsupervised Pretraining with Region Priors for Object Detection

DETReg: Unsupervised Pretraining with Region Priors for Object Detection Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik

Amir Bar 283 Dec 27, 2022
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

Zhiqiang Shen 16 Nov 4, 2020
Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Welcome to Barlow Barlow is a tool for identifying the failure modes for a given neural network. To achieve this, Barlow first creates a group of imag

Sahil Singla 33 Dec 5, 2022
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

pytorch-a2c-ppo-acktr Update (April 12th, 2021) PPO is great, but Soft Actor Critic can be better for many continuous control tasks. Please check out

Ilya Kostrikov 3k Jan 9, 2023
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

Ilya Kostrikov 3k Dec 31, 2022
Deep Image Search is an AI-based image search engine that includes deep transfor learning features Extraction and tree-based vectorized search.

Deep Image Search - AI-Based Image Search Engine Deep Image Search is an AI-based image search engine that includes deep transfer learning features Ex

null 139 Jan 1, 2023
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs This is an implemetation of the paper Few-shot Relation Extraction via Baye

MilaGraph 36 Nov 22, 2022
Trajectory Extraction of road users via Traffic Camera

Traffic Monitoring Citation The associated paper for this project will be published here as soon as possible. When using this software, please cite th

Julian Strosahl 14 Dec 17, 2022