Official Repository for our ICCV2021 paper: Continual Learning on Noisy Data Streams via Self-Purified Replay

Related tags

Deep LearningSPR
Overview

Continual Learning on Noisy Data Streams via Self-Purified Replay

This repository contains the official PyTorch implementation for our ICCV2021 paper.

  • Chris Dongjoo Kim*, Jinseo Jeong*, Sangwoo Moon, Gunhee Kim. Continual Learning on Noisy Data Streams via Self-Purified Replay. In ICCV, 2021 (* equal contribution).

[Paper Link][Slides][Poster]

System Dependencies

  • Python >= 3.6.1
  • CUDA >= 9.0 supported GPU

Installation

Using virtual env is recommended.

$ conda create --name SPR python=3.6

Install pytorch==1.7.0 and torchvision==0.8.1. Then, install the rest of the requirements.

$ pip install -r requirements.txt

Data and Log directory set-up

create checkpoints and data directories. We recommend symbolic links as below.

$ mkdir data
$ ln -s [MNIST Data Path] data/mnist
$ ln -s [CIFAR10 Data Path] data/cifar10
$ ln -s [CIFAR100 Data Path] data/cifar100
$ ln -s [Webvision Data Path] data/webvision

$ ln -s [log directory path] checkpoints

Run

Specify parameters in config yaml, episodes yaml files.

python main.py --log-dir [log directory path] --c [config file path] --e [episode file path] --override "|" --random_seed [seed]

# e.g. to run mnist symmetric noise 40% experiment,
python main.py --log-dir [log directory path] --c configs/mnist_spr.yaml --e episodes/mnist-split_epc1_a.yaml --override "corruption_percent=0.4";

# e.g. to run cifar10 asymmetric noise 40% experiment,
python main.py --log-dir [log directory path] --c configs/cifar10_spr.yaml --e episodes/cifar10-split_epc1_asym_a.yaml --override "asymmetric_nosie=False|corruption_percent=0.4";

# e.g. to run cifar100 superclass symmetric noise 40% experiment,
python main.py --log-dir [log directory path] --c configs/cifar100_spr.yaml --e episodes/cifar100sup-split_epc1_a.yaml --override "superclass_nosie=True|corruption_percent=0.4";

Expert Parallel Training

If you use slurm environment, training expert models in advance is possible.

# e.g. to run mnist symmetric noise 40% experiment,
python meta-main.py --log-dir [log directory path] -c configs/mnist_spr.yaml -e episodes/mnist-split_epc1_a.yaml --random_seed [seed] --override "corruption_percent=0.4" --njobs 10 --jobs_per_gpu 3

# also, you can only train experts for later use by adding an --expert_train_only option.
python meta-main.py --log-dir [log directory path] -c configs/mnist_spr.yaml -e episodes/mnist-split_epc1_a.yaml --random_seed [seed] --override "corruption_percent=0.4" --ngpu 10 --jobs_per_gpu 3 --expert_train_only

## to use the trained experts, set the same [log directory path] and [seed].
python main.py --log-dir [log directory path] --c configs/mnist_spr.yaml --e episodes/mnist-split_epc1_a.yaml --random_seed [seed] --override "corruption_percent=0.4";

Citation

The code and dataset are free to use for academic purposes only. If you use any of the material in this repository as part of your work, we ask you to cite:

@inproceedings{kim-ICCV-2021,
    author    = {Chris Dongjoo Kim and Jinseo Jeong and Sangwoo Moon and Gunhee Kim},
    title     = "{Continual Learning on Noisy Data Streams via Self-Purified Replay}"
    booktitle = {ICCV},
    year      = 2021
}

Last edit: Oct 12, 2021

Owner
Jinseo Jeong
graduate student @ vision & learning lab, Seoul National Univ.
Jinseo Jeong
Deep Text Search is an AI-powered multilingual text search and recommendation engine with state-of-the-art transformer-based multilingual text embedding (50+ languages).

Deep Text Search - AI Based Text Search & Recommendation System Deep Text Search is an AI-powered multilingual text search and recommendation engine w

19 Sep 29, 2022
On Out-of-distribution Detection with Energy-based Models

On Out-of-distribution Detection with Energy-based Models This repository contains the code for the experiments conducted in the paper On Out-of-distr

Sven 19 Aug 07, 2022
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

wsss-analysis The code of: A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains, arXiv pre-print 2019 paper.

Lyndon Chan 48 Dec 18, 2022
Python scripts for performing object detection with the 1000 labels of the ImageNet dataset in ONNX.

Python scripts for performing object detection with the 1000 labels of the ImageNet dataset in ONNX. The repository combines a class agnostic object localizer to first detect the objects in the image

Ibai Gorordo 24 Nov 14, 2022
LRBoost is a scikit-learn compatible approach to performing linear residual based stacking/boosting.

LRBoost is a sckit-learn compatible package for linear residual boosting. LRBoost combines a linear estimator and a non-linear estimator to leverage t

Andrew Patton 5 Nov 23, 2022
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

SVHNClassifier-PyTorch A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks If

Potter Hsu 182 Jan 03, 2023
Official implementation of the NRNS paper: No RL, No Simulation: Learning to Navigate without Navigating

No RL No Simulation (NRNS) Official implementation of the NRNS paper: No RL, No Simulation: Learning to Navigate without Navigating NRNS is a heriarch

Meera Hahn 20 Nov 29, 2022
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)

Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models Pouya Samangouei*, Maya Kabkab*, Rama Chellappa [*: authors co

Maya Kabkab 212 Dec 07, 2022
This repository contains the code for TABS, a 3D CNN-Transformer hybrid automated brain tissue segmentation algorithm using T1w structural MRI scans

This repository contains the code for TABS, a 3D CNN-Transformer hybrid automated brain tissue segmentation algorithm using T1w structural MRI scans. TABS relies on a Res-Unet backbone, with a Vision

6 Nov 07, 2022
This repo provides the base code for pytorch-lightning and weight and biases simultaneous integration.

Write your model faster with pytorch-lightning-wadb-code-backbone This repository provides the base code for pytorch-lightning and weight and biases s

9 Mar 29, 2022
Revisiting Self-Training for Few-Shot Learning of Language Model.

SFLM This is the implementation of the paper Revisiting Self-Training for Few-Shot Learning of Language Model. SFLM is short for self-training for few

15 Nov 19, 2022
A bare-bones Python library for quality diversity optimization.

pyribs Website Source PyPI Conda CI/CD Docs Docs Status Twitter pyribs.org GitHub docs.pyribs.org A bare-bones Python library for quality diversity op

ICAROS 127 Jan 06, 2023
Let's Git - Versionsverwaltung & Open Source Hausaufgabe

Let's Git - Versionsverwaltung & Open Source Hausaufgabe Herzlich Willkommen zu dieser Hausaufgabe für unseren MOOC: Let's Git! Wir hoffen, dass Du vi

1 Dec 13, 2021
Tiny-NewsRec: Efficient and Effective PLM-based News Recommendation

Tiny-NewsRec The source codes for our paper "Tiny-NewsRec: Efficient and Effective PLM-based News Recommendation". Requirements PyTorch == 1.6.0 Tensor

Yang Yu 3 Dec 07, 2022
AgML is a comprehensive library for agricultural machine learning

AgML is a comprehensive library for agricultural machine learning. Currently, AgML provides access to a wealth of public agricultural datasets for common agricultural deep learning tasks.

Plant AI and Biophysics Lab 1 Jul 07, 2022
Direct design of biquad filter cascades with deep learning by sampling random polynomials.

IIRNet Direct design of biquad filter cascades with deep learning by sampling random polynomials. Usage git clone https://github.com/csteinmetz1/IIRNe

Christian J. Steinmetz 55 Nov 02, 2022
Preparation material for Dropbox interviews

Dropbox-Onsite-Interviews A guide for the Dropbox onsite interview! The Dropbox interview question bank is very small. The bank has been in a Chinese

386 Dec 31, 2022
Source code for our paper "Do Not Trust Prediction Scores for Membership Inference Attacks"

Do Not Trust Prediction Scores for Membership Inference Attacks Abstract: Membership inference attacks (MIAs) aim to determine whether a specific samp

<a href=[email protected]"> 3 Oct 25, 2022
MoveNet Single Pose on OpenVINO

MoveNet Single Pose tracking on OpenVINO Running Google MoveNet Single Pose models on OpenVINO. A convolutional neural network model that runs on RGB

35 Nov 11, 2022
CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

CPT This repository contains code and checkpoints for CPT. CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Gener

fastNLP 341 Dec 29, 2022