SCNet: Learning Semantic Correspondence

Related tags

Deep LearningSCNet
Overview

SCNet Code

Region matching code is contributed by Kai Han ([email protected]).

Dense matching code is contributed by Rafael S. Rezende ([email protected]).

This code is written in MATLAB, and implements the SCNet[1]. For the dataset, see our project page: http://www.di.ens.fr/willow/research/scnet.

Install Dependencies

Codes

SCNet_Matconvnet

Additional Matconvnet modules implemented for SCNet. These code should be copied into matconvnet/matlab/ folder.

SCNet

This is the primary net work training and testing code.

  • SCNet_A_init.m, SCNet_AG_init.m, SCNet_AGplus_init.m: initialize the SCNet_A, SCNet_AG, SCNet_AG+.

  • SCNet_A.m, SCNet_AG.m, SCNet_AGplus.m: train SCNet_A, SCNet_AG, SCNet_AG+.

  • eva_PCR_mIoU_SCNet_A.m, eva_PCR_mIoU_SCNet_AG.m, eva_PCR_mIoU_SCNet_AGplus.m: evaluate the trained nets.

  • eva_PCR_mIoU_ImageNet_SCNet_A.m, eva_PCR_mIoU_ImageNet_SCNet_AG.m, eva_PCR_mIoU_ImageNet_SCNet_AGplus.m: evaluate SCNets with ImageNet pretrained parameters, i.e., SCNets without training.

SCNet_Baselines

Comparison code for our SCNet features and HOG features with NAM, PHM and LOM in Proposal Flow [2, 3].

  • NAM_HOG_eva.m, PHM_HOG_eva.m, LOM_HOG_eva.m: evaluate NAM, PHM, and LOM with HOG features.

  • NAM_SCNet_eva.m, PHM_SCNet_eva.m, LOM_SCNet_eva.m: evaluate NAM, PHM, and LOM with learned SCNet features.

  • HOG_SCNet_AG_eva.m: replace the learned SCNet feature by HOG feature in SCNet_AG model.

Data

We used PF-PASCAL, PF-WILLOW, PASCAL Parts and CUB data sets and follows Proposal Flow[2, 3] to generate our trainging data.

Triaining data preparation code is put in PF-PASCAL-code folder.

Notes

  • The code is provided for academic use only. Use of the code in any commercial or industrial related activities is prohibited.
  • If you use our code or dataset, please cite the paper.
@InProceedings{han2017scnet,
author = {Kai Han and Rafael S. Rezende and Bumsub Ham and Kwan-Yee K. Wong and Minsu Cho and Cordelia Schmid and Jean Ponce},
title = {SCNet: Learning Semantic Correspondence},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2017}
}

References

[1] Kai Han, Rafael S. Rezende, Bumsub Ham, Kwan-Yee K. Wong, Minsu Cho, Cordelia Schmid, Jean Ponce, "SCNet: Learning Semantic Correspondence", International Conference on Computer Vision (ICCV), 2017.

[2] Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce, "Proposal Flow: Semantic Correspondences from Object Proposals", IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2017

[3] Bumsub Ham, Minsu Cho, Cordelia Schmid, Jean Ponce, "Proposal Flow", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

Owner
Kai Han
Visual Geometry Group (VGG)
Kai Han
Blind visual quality assessment on 360° Video based on progressive learning

Blind visual quality assessment on omnidirectional or 360 video (ProVQA) Blind VQA for 360° Video via Progressively Learning from Pixels, Frames and V

5 Jan 06, 2023
Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · R. Huang

code for "Improving GAN Training via Binarized Representation Entropy (BRE) Regularization" (ICLR2018 paper) paper: https://arxiv.org/abs/1805.03644 G

21 Oct 12, 2020
[ICML 2020] "When Does Self-Supervision Help Graph Convolutional Networks?" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen

When Does Self-Supervision Help Graph Convolutional Networks? PyTorch implementation for When Does Self-Supervision Help Graph Convolutional Networks?

Shen Lab at Texas A&M University 106 Nov 11, 2022
AI assistant built in python.the features are it can display time,say weather,open-google,youtube,instagram.

AI assistant built in python.the features are it can display time,say weather,open-google,youtube,instagram.

AK-Shanmugananthan 1 Nov 29, 2021
Data-depth-inference - Data depth inference with python

Welcome! This readme will guide you through the use of the code in this reposito

Marco 3 Feb 08, 2022
Keras udrl - Keras implementation of Upside Down Reinforcement Learning

keras_udrl Keras implementation of Upside Down Reinforcement Learning This is me

Eder Santana 7 Jan 24, 2022
Clockwork Convnets for Video Semantic Segmentation

Clockwork Convnets for Video Semantic Segmentation This is the reference implementation of arxiv:1608.03609: Clockwork Convnets for Video Semantic Seg

Evan Shelhamer 141 Nov 21, 2022
A Simulation Environment to train Robots in Large Realistic Interactive Scenes

iGibson: A Simulation Environment to train Robots in Large Realistic Interactive Scenes iGibson is a simulation environment providing fast visual rend

Stanford Vision and Learning Lab 493 Jan 04, 2023
Pytorch modules for paralel models with same architecture. Ideal for multi agent-based systems

WideLinears Pytorch parallel Neural Networks A package of pytorch modules for fast paralellization of separate deep neural networks. Ideal for agent-b

1 Dec 17, 2021
This is a simple plugin for Vim that allows you to use OpenAI Codex.

🤖 Vim Codex An AI plugin that does the work for you. This is a simple plugin for Vim that will allow you to use OpenAI Codex. To use this plugin you

Tom Dörr 195 Dec 28, 2022
Improving Non-autoregressive Generation with Mixup Training

MIST Training MIST TRAIN_FILE=/your/path/to/train.json VALID_FILE=/your/path/to/valid.json OUTPUT_DIR=/your/path/to/save_checkpoints CACHE_DIR=/your/p

7 Nov 22, 2022
Multiple-Object Tracking with Transformer

TransTrack: Multiple-Object Tracking with Transformer Introduction TransTrack: Multiple-Object Tracking with Transformer Models Training data Training

Peize Sun 537 Jan 04, 2023
IGCN : Image-to-graph convolutional network

IGCN : Image-to-graph convolutional network IGCN is a learning framework for 2D/3D deformable model registration and alignment, and shape reconstructi

Megumi Nakao 7 Oct 27, 2022
Accompanying code for the paper "A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment".

#backdoor-HSIC (bd_HSIC) Accompanying code for the paper "A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment". To generate

Robert Hu 0 Nov 25, 2021
Neural Dynamic Policies for End-to-End Sensorimotor Learning

This is a PyTorch based implementation for our NeurIPS 2020 paper on Neural Dynamic Policies for end-to-end sensorimotor learning.

Shikhar Bahl 47 Dec 11, 2022
Confidence Propagation Cluster aims to replace NMS-based methods as a better box fusion framework in 2D/3D Object detection

CP-Cluster Confidence Propagation Cluster aims to replace NMS-based methods as a better box fusion framework in 2D/3D Object detection, Instance Segme

Yichun Shen 41 Dec 08, 2022
Very deep VAEs in JAX/Flax

Very Deep VAEs in JAX/Flax Implementation of the experiments in the paper Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on I

Jamie Townsend 42 Dec 12, 2022
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

[AAAI2022] Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics Overall pipeline of OCN. Paper Link: [arXiv] [AAAI

13 Nov 21, 2022
This is an easy python software which allows to sort images with faces by gender and after by age.

Gender-age Classifier This is an easy python software which allows to sort images with faces by gender and after by age. Usage First install Deepface

Claudio Ciccarone 6 Sep 17, 2022