Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Overview

Dataset Distillation by Matching Training Trajectories

Project Page | Paper


Teaser image

This repo contains code for training expert trajectories and distilling synthetic data from our Dataset Distillation by Matching Training Trajectories paper (CVPR 2022). Please see our project page for more results.

Dataset Distillation by Matching Training Trajectories
George Cazenavette, Tongzhou Wang, Antonio Torralba, Alexei A. Efros, Jun-Yan Zhu
CMU, MIT, UC Berkeley
CVPR 2022

The task of "Dataset Distillation" is to learn a small number of synthetic images such that a model trained on this set alone will have similar test performance as a model trained on the full real dataset.

Our method distills the synthetic dataset by directly optimizing the fake images to induce similar network training dynamics as the full, real dataset. We train "student" networks for many iterations on the synthetic data, measure the error in parameter space between the "student" and "expert" networks trained on real data, and back-propagate through all the student network updates to optimize the synthetic pixels.

Wearable ImageNet: Synthesizing Tileable Textures

Teaser image

Instead of treating our synthetic data as individual images, we can instead encourage every random crop (with circular padding) on a larger canvas of pixels to induce a good training trajectory. This results in class-based textures that are continuous around their edges.

Given these tileable textures, we can apply them to areas that require such properties, such as clothing patterns.

Visualizations made using FAB3D

Getting Started

First, download our repo:

git clone https://github.com/GeorgeCazenavette/mtt-distillation.git
cd mtt-distillation

For an express instillation, we include .yaml files.

If you have an RTX 30XX GPU (or newer), run

conda env create -f requirements_11_3.yaml

If you have an RTX 20XX GPU (or older), run

conda env create -f requirements_10_2.yaml

You can then activate your conda environment with

conda activate distillation
Quadro Users Take Note:

torch.nn.DataParallel seems to not work on Quadro A5000 GPUs, and this may extend to other Quadro cards.

If you experience indefinite hanging during training, try running the process with only 1 GPU by prepending CUDA_VISIBLE_DEVICES=0 to the command.

Generating Expert Trajectories

Before doing any distillation, you'll need to generate some expert trajectories using buffer.py

The following command will train 100 ConvNet models on CIFAR-100 with ZCA whitening for 50 epochs each:

python buffer.py --dataset=CIFAR100 --model=ConvNet --train_epochs=50 --num_experts=100 --zca --buffer_path={path_to_buffer_storage} --data_path={path_to_dataset}

We used 50 epochs with the default learning rate for all of our experts. Worse (but still interesting) results can be obtained faster through training fewer experts by changing --num_experts. Note that experts need only be trained once and can be re-used for multiple distillation experiments.

Distillation by Matching Training Trajectories

The following command will then use the buffers we just generated to distill CIFAR-100 down to just 1 image per class:

python distill.py --dataset=CIFAR100 --ipc=1 --syn_steps=20 --expert_epochs=3 --max_start_epoch=20 --zca --lr_img=1000 --lr_lr=1e-05 --lr_teacher=0.01 --buffer_path={path_to_buffer_storage} --data_path={path_to_dataset}

ImageNet

Our method can also distill subsets of ImageNet into low-support synthetic sets.

When generating expert trajectories with buffer.py or distilling the dataset with distill.py, you must designate a named subset of ImageNet with the --subset flag.

For example,

python distill.py --dataset=ImageNet --subset=imagefruit --model=ConvNetD5 --ipc=1 --res=128 --syn_steps=20 --expert_epochs=2 --max_start_epoch=10 --lr_img=1000 --lr_lr=1e-06 --lr_teacher=0.01 --buffer_path={path_to_buffer_storage} --data_path={path_to_dataset}

will distill the imagefruit subset (at 128x128 resolution) into the following 10 images

To register your own ImageNet subset, you can add it to the Config class at the top of utils.py.

Simply create a list with the desired class ID's and add it to the dictionary.

This gist contains a list of all 1k ImageNet classes and their corresponding numbers.

Texture Distillation

You can also use the same set of expert trajectories (except those using ZCA) to distill classes into toroidal textures by simply adding the --texture flag.

For example,

python distill.py --texture --dataset=ImageNet --subset=imagesquawk --model=ConvNetD5 --ipc=1 --res=256 --syn_steps=20 --expert_epochs=2 --max_start_epoch=10 --lr_img=1000 --lr_lr=1e-06 --lr_teacher=0.01 --buffer_path={path_to_buffer_storage} --data_path={path_to_dataset}

will distill the imagesquawk subset (at 256x256 resolution) into the following 10 textures

Acknowledgments

We would like to thank Alexander Li, Assaf Shocher, Gokul Swamy, Kangle Deng, Ruihan Gao, Nupur Kumari, Muyang Li, Gaurav Parmar, Chonghyuk Song, Sheng-Yu Wang, and Bingliang Zhang as well as Simon Lucey's Vision Group at the University of Adelaide for their valuable feedback. This work is supported, in part, by the NSF Graduate Research Fellowship under Grant No. DGE1745016 and grants from J.P. Morgan Chase, IBM, and SAP. Our code is adapted from https://github.com/VICO-UoE/DatasetCondensation

Related Work

  1. Tongzhou Wang et al. "Dataset Distillation", in arXiv preprint 2018
  2. Bo Zhao et al. "Dataset Condensation with Gradient Matching", in ICLR 2020
  3. Bo Zhao and Hakan Bilen. "Dataset Condensation with Differentiable Siamese Augmentation", in ICML 2021
  4. Timothy Nguyen et al. "Dataset Meta-Learning from Kernel Ridge-Regression", in ICLR 2021
  5. Timothy Nguyen et al. "Dataset Distillation with Infinitely Wide Convolutional Networks", in NeurIPS 2021
  6. Bo Zhao and Hakan Bilen. "Dataset Condensation with Distribution Matching", in arXiv preprint 2021
  7. Kai Wang et al. "CAFE: Learning to Condense Dataset by Aligning Features", in CVPR 2022

Reference

If you find our code useful for your research, please cite our paper.

@inproceedings{
cazenavette2022distillation,
title={Dataset Distillation by Matching Training Trajectories},
author={George Cazenavette and Tongzhou Wang and Antonio Torralba and Alexei A. Efros and Jun-Yan Zhu},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2022}
}
Owner
George Cazenavette
Carnegie Mellon University
George Cazenavette
A python package to perform same transformation to coco-annotation as performed on the image.

coco-transform-util A python package to perform same transformation to coco-annotation as performed on the image. Installation Way 1 $ git clone https

1 Jan 14, 2022
Implementation of TimeSformer, a pure attention-based solution for video classification

TimeSformer - Pytorch Implementation of TimeSformer, a pure and simple attention-based solution for reaching SOTA on video classification.

Phil Wang 602 Jan 03, 2023
🔥 Cogitare - A Modern, Fast, and Modular Deep Learning and Machine Learning framework for Python

Cogitare is a Modern, Fast, and Modular Deep Learning and Machine Learning framework for Python. A friendly interface for beginners and a powerful too

Cogitare - Modern and Easy Deep Learning with Python 76 Sep 30, 2022
Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021)

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021) Alexey Nekrasov*, Jonas Schult*, Or Litany, Bastian Leibe, Francis Engelmann Mix3D is

Alexey Nekrasov 189 Dec 26, 2022
Code to reproduce the results for Statistically Robust Neural Network Classification, published in UAI 2021

Code to reproduce the results for Statistically Robust Neural Network Classification, published in UAI 2021

1 Jun 02, 2022
NEG loss implemented in pytorch

Pytorch Negative Sampling Loss Negative Sampling Loss implemented in PyTorch. Usage neg_loss = NEG_loss(num_classes, embedding_size) optimizer =

Daniil Gavrilov 123 Sep 13, 2022
Does Oversizing Improve Prosumer Profitability in a Flexibility Market? - A Sensitivity Analysis using PV-battery System

Does Oversizing Improve Prosumer Profitability in a Flexibility Market? - A Sensitivity Analysis using PV-battery System The possibilities to involve

Babu Kumaran Nalini 0 Nov 19, 2021
Official implementation of the paper "Topographic VAEs learn Equivariant Capsules"

Topographic Variational Autoencoder Paper: https://arxiv.org/abs/2109.01394 Getting Started Install requirements with Anaconda: conda env create -f en

T. Andy Keller 69 Dec 12, 2022
Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging

ShICA Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging Install Move into the ShICA directory cd ShICA

8 Nov 07, 2022
We simulate traveling back in time with a modern camera to rephotograph famous historical subjects.

[SIGGRAPH Asia 2021] Time-Travel Rephotography [Project Website] Many historical people were only ever captured by old, faded, black and white photos,

298 Jan 02, 2023
OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework Introduction OpenFed is a foundational library for federated learning

25 Dec 12, 2022
All materials of Cassandra Event, Udyam'22

Cassandra 2022 Workspace Workshop Materials Workshop-1 Workshop-2 Workshop-3 Workshop-4 Assignments Assignment-1 Assignment-2 Assignment-3 Resources P

36 Dec 31, 2022
pip install python-office

🍬 python for office 👉 http://www.python4office.cn/ 👈 🌎 English Documentation 📚 简介 Python-office 是一个 Python 自动化办公第三方库,能解决大部分自动化办公的问题。而且每个功能只需一行代码,

程序员晚枫 272 Dec 29, 2022
In this project we use both Resnet and Self-attention layer for cat, dog and flower classification.

cdf_att_classification classes = {0: 'cat', 1: 'dog', 2: 'flower'} In this project we use both Resnet and Self-attention layer for cdf-Classification.

3 Nov 23, 2022
The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition Boyan Zhou, Quan Cui, Xiu-Shen Wei*, Zhao-Min Chen This repo

Megvii-Nanjing 616 Dec 21, 2022
A package, and script, to perform imaging transcriptomics on a neuroimaging scan.

Imaging Transcriptomics Imaging transcriptomics is a methodology that allows to identify patterns of correlation between gene expression and some prop

Alessio Giacomel 10 Dec 27, 2022
CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax ⚠️ Latest: Current repo is a complete version. But we delet

FishYuLi 341 Dec 23, 2022
A program that uses computer vision to detect hand gestures, used for controlling movie players.

HandGestureDetection This program uses a Haar Cascade algorithm to detect the presence of your hand, and then passes it on to a self-created and self-

2 Nov 22, 2022
Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)

Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019) Introduction Official implementation of Dynamic Multi-scale Filters for Semant

23 Oct 21, 2022