PyTorch implementation of Self-supervised Contrastive Regularization for DG (SelfReg)

Related tags

Deep LearningSelfReg
Overview

SelfReg

PyTorch official implementation of Self-supervised Contrastive Regularization for Domain Generalization (SelfReg, https://arxiv.org/abs/2104.09841)

Description

method An overview of our proposed SelfReg. Here, we propose to use the self-supervised (in-batch) contrastive losses to regularize the model to learn domain-invariant representations. These losses regularize the model to map the representations of the "same-class" samples close together in the embedding space. We compute the following two dissimilarities in the embedding space: (i) individualized and (ii) heterogeneous self-supervised dissimilarity losses. We further use the stochastic weight average (SWA) technique and the inter-domain curriculum learning (IDCL) to optimize gradients in conflict directions.

tsne Visualizations by t-SNE for (a) baseline (no DG techniques), (b) RSC, and (c) ours. For better understanding, we also provide sample images of house from all target domains. Note that we differently color-coded each points according to its class. (Data: PACS)

Computational Efficiency of IDCL (Inter-domain Curriculum Learning)

Backbone Training Strategy Training Time(s)
ResNet-18 Baseline (classic training strategy) 1556.8
ResNet-18 IDCL strategy 1283.5

We used one V100 GPU for model training. The training time in above table is the time it took to train all domains independently. The training time of the IDCL is 1283.5 seconds, equivalent to 82.4% of baseline on PACS.

Dependency

  • python >= 3.6
  • pytorch >= 1.7.0
  • torchvision >= 0.8.1
  • jupyter notebook
  • gdown

How to Use

  1. cd codes/ and sh download.sh to download PACS dataset.
  2. Open train.ipynb and Run All.
  3. Make sure that the training is running well in the last cell.
  4. Check the results stored in path codes/resnet18/{save_name}/ when the training is completed.

Test trained SelfReg ResNet18 model

To test a ResNet18, you can download pretrained weights (SelfReg model) with this link.

These weights are wrapped torch.optim.swa_utils.AveragedModel() (SWA implementation of PyTorch).

Backbone Target Domain Acc %
ResNet-18 Photo 96.83
ResNet-18 Art Painting 83.15
ResNet-18 Cartoon 79.61
ResNet-18 Sketch 78.90

Benchmark of SelfReg in DomainBed

domainbed

FluxTraining.jl gives you an endlessly extensible training loop for deep learning

A flexible neural net training library inspired by fast.ai

86 Dec 31, 2022
Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

512x512 flowers after 12 hours of training, 1 gpu 256x256 flowers after 12 hours of training, 1 gpu Pizza 'Lightweight' GAN Implementation of 'lightwe

Phil Wang 1.5k Jan 02, 2023
The pure and clear PyTorch Distributed Training Framework.

The pure and clear PyTorch Distributed Training Framework. Introduction Requirements and Usage Dependency Dataset Basic Usage Slurm Cluster Usage Base

WILL LEE 208 Dec 20, 2022
Retrieval.pytorch - The code we used in [2020 DIGIX]

Retrieval.pytorch - The code we used in [2020 DIGIX]

Guo-Hua Wang 2 Feb 07, 2022
PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)

PSTR (CVPR2022) This code is an official implementation of "PSTR: End-to-End One-Step Person Search With Transformers (CVPR2022)". End-to-end one-step

Jiale Cao 28 Dec 13, 2022
Code and dataset for ACL2018 paper "Exploiting Document Knowledge for Aspect-level Sentiment Classification"

Aspect-level Sentiment Classification Code and dataset for ACL2018 [paper] ‘‘Exploiting Document Knowledge for Aspect-level Sentiment Classification’’

Ruidan He 146 Nov 29, 2022
Implementation of Ag-Grid component for Streamlit

streamlit-aggrid AgGrid is an awsome grid for web frontend. More information in https://www.ag-grid.com/. Consider purchasing a license from Ag-Grid i

Pablo Fonseca 556 Dec 31, 2022
Evaluating deep transfer learning for whole-brain cognitive decoding

Evaluating deep transfer learning for whole-brain cognitive decoding This README file contains the following sections: Project description Repository

Armin Thomas 5 Oct 31, 2022
Numerical Methods with Python, Numpy and Matplotlib

Numerical Bric-a-Brac Collections of numerical techniques with Python and standard computational packages (Numpy, SciPy, Numba, Matplotlib ...). Diffe

Vincent Bonnet 10 Dec 20, 2021
Learning What and Where to Draw

###Learning What and Where to Draw Scott Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, Honglak Lee This is the code for our NIPS 201

Scott Ellison Reed 337 Nov 18, 2022
DeconvNet : Learning Deconvolution Network for Semantic Segmentation

DeconvNet: Learning Deconvolution Network for Semantic Segmentation Created by Hyeonwoo Noh, Seunghoon Hong and Bohyung Han at POSTECH Acknowledgement

Hyeonwoo Noh 325 Oct 20, 2022
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

Bootstrap Your Own Latent (BYOL), in Pytorch Practical implementation of an astoundingly simple method for self-supervised learning that achieves a ne

Phil Wang 1.4k Dec 29, 2022
Pytorch implementation for "Implicit Semantic Response Alignment for Partial Domain Adaptation"

Implicit-Semantic-Response-Alignment Pytorch implementation for "Implicit Semantic Response Alignment for Partial Domain Adaptation" Prerequisites pyt

4 Dec 19, 2022
You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2

You Only Look One-level Feature (YOLOF), CVPR2021 A simple, fast, and efficient object detector without FPN. This repo provides a neat implementation

qiang chen 273 Jan 03, 2023
Unsupervised phone and word segmentation using dynamic programming on self-supervised VQ features.

Unsupervised Phone and Word Segmentation using Vector-Quantized Neural Networks Overview Unsupervised phone and word segmentation on speech data is pe

Herman Kamper 13 Dec 11, 2022
Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet, CVPR2021 安全AI挑战者计划第六期:ImageNet无限制对抗攻击 决赛第四名(team name: Advers)

51 Dec 01, 2022
Deep Compression for Dense Point Cloud Maps.

DEPOCO This repository implements the algorithms described in our paper Deep Compression for Dense Point Cloud Maps. How to get started (using Docker)

Photogrammetry & Robotics Bonn 67 Dec 06, 2022
LQM - Improving Object Detection by Estimating Bounding Box Quality Accurately

Improving Object Detection by Estimating Bounding Box Quality Accurately Abstract Object detection aims to locate and classify object instances in ima

IM Lab., POSTECH 0 Sep 28, 2022
Unofficial Pytorch Implementation of WaveGrad2

WaveGrad 2 — Unofficial PyTorch Implementation WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis Unofficial PyTorch+Lightning Implementati

MINDs Lab 104 Nov 29, 2022
Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving

Visual 3D Detection Package: This repo aims to provide flexible and reproducible visual 3D detection on KITTI dataset. We expect scripts starting from

Yuxuan Liu 305 Dec 19, 2022