Code for Active Learning at The ImageNet Scale.

Related tags

Deep Learning active_learning
Overview

Active Learning at the ImageNet Scale

This repo contains code for the paper Active Learning at the ImageNet Scale by Zeyad Emam*, Hong-Min Chu*, Ping-Yeh Chiang*, Wojtek Czaja, Richard Leapman, Micah Goldblum, and Tom Goldstein.

Requirements

pip install -r requirements.txt

Comet and Logging

This project uses Comet ML to log all experiments, you must install comet_ml (included in requirements.txt), however, the code does not require the user to have a Comet ML account or to enable comet logging at all. If you choose to use comet ML, then you should include your API key in your home directory ~/.comet.config (more on this in the Comet ML documentation). To use comet make sure the use the flag --enable_comet.

Logs and network weights are stored according to the command line arguments --log_dir and --ckpt_path.

Loading SSP checkpoints

Self-supervised pretrained checkpoints must be obtained separately and specified in ./src/arg_pools for each argpool, under the key "init_pretrained_ckpt_path". To access the checkpoints used in our experiments, please use the following links:

Sample Commands to Reproduce the Results in the Paper

Each Imagenet experiment was conducted on a cluster node with a single V100-SXM2 GPU (32GB VRAM), 64gb of RAM, and 16 2.3 GHz Intel Gold 6140 cpus. If more than one gpu are available on the node, the code will automatically distribute batches across all gpus using DistributedDataParallel training.

Below is a sample command for running an experiment. The full list of command line arguments can be found in src/utils/parser.py.

python main_al.py --dataset_dir 
   
     --exp_name RandomSampler_arg_ssp_linear_evaluation_imagenet_b10000 --dataset imagenet --arg_pool ssp_linear_evaluation --model SSLResNet50 --strategy RandomSampler --rounds 8 --round_budget 10000 --init_pool_size 30000 --subset_labeled 50000 --subset_unlabeled 80000 --freeze_feature --partitions 10 --init_pool_type random

The full list of commands to reproduce all plots in the paper can be obtained by running python src/gen_jobs.py.

You might also like...
transfer attack; adversarial examples; black-box attack; unrestricted Adversarial Attacks on ImageNet; CVPR2021 天池黑盒竞赛
transfer attack; adversarial examples; black-box attack; unrestricted Adversarial Attacks on ImageNet; CVPR2021 天池黑盒竞赛

transfer_adv CVPR-2021 AIC-VI: unrestricted Adversarial Attacks on ImageNet CVPR2021 安全AI挑战者计划第六期赛道2：ImageNet无限制对抗攻击 介绍 ： 深度神经网络已经在各种视觉识别问题上取得了最先进的性能。

null 25 Dec 8, 2022
Pytorch implementation of
Pytorch implementation of "Training a 85.4% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet"

Token Labeling: Training an 85.4% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet (arxiv) This is a Pytorch implementation of our te

蒋子航 383 Dec 27, 2022
Official Pytorch Implementation of:
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

ImageNet-21K Pretraining for the Masses Paper | Pretrained models Official PyTorch Implementation Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, Lihi Zelni

null 574 Jan 2, 2023
A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

Tom 50 Dec 16, 2022
A small demonstration of using WebDataset with ImageNet and PyTorch Lightning

A small demonstration of using WebDataset with ImageNet and PyTorch Lightning This is a small repo illustrating how to use WebDataset on ImageNet. usi

null 50 Dec 16, 2022
PyTorch implementation of PNASNet-5 on ImageNet

PNASNet.pytorch PyTorch implementation of PNASNet-5. Specifically, PyTorch code from this repository is adapted to completely match both my implemetat

Chenxi Liu 314 Nov 25, 2022
Vanilla and Prototypical Networks with Random Weights for image classification on Omniglot and mini-ImageNet. Made with Python3.

vanilla-rw-protonets-project Vanilla Prototypical Networks and PNs with Random Weights for image classification on Omniglot and mini-ImageNet. Made wi

Giovani Candido 8 Aug 31, 2022
PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Reference-Based-Sketch-Image-Colorization-ImageNet This is a PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization usin

Yuzhi ZHAO 11 Jul 28, 2022
ImageNet-CoG is a benchmark for concept generalization. It provides a full evaluation framework for pre-trained visual representations which measure how well they generalize to unseen concepts.

The ImageNet-CoG Benchmark Project Website Paper (arXiv) Code repository for the ImageNet-CoG Benchmark introduced in the paper "Concept Generalizatio

NAVER 23 Oct 9, 2022
Comments
  • Regarding related work on trying AL on fixed self-supervised model

    Regarding related work on trying AL on fixed self-supervised model

    In the end of section 3 of your paper, you described "Consequently, it is important to evaluate AL algorithms when the feature extractor is fixed and only the classifica-tion head is finetuned. This task is a common benchmark inself-supervised learning (SSL) research [13, 14, 26], wherethe proposed SSL method is used to pretrain the network’sfeature extractor, then a linear classification head is trained on the features in a fully-supervised fashion. However, tothe best of our knowledge, AL strategies on ImageNet havenot been evaluated in this specific setting."

    There actually seems to be a previous work that did just this. Please check out the paper "Reducing Label Effort: Self-Supervised meets Active Learning" published on August, 2021. link: https://arxiv.org/abs/2108.11458 image

    opened by krenerd 1
  • The Computation of Normal Vector of DB

    The Computation of Normal Vector of DB

    Hi, I cannot understand the computation of normal vectors of DBs in the source code. Because I think the weights of the linear layer in current models can be expressed as the normal vectors of DBs, why do we need to calculate the \delta_weight and epsilon? Could you please reply when you are free? I have been troubled by this problem for a long time, which makes it difficult for me to fundamentally understand the essence of the algorithm.

    opened by junzhang-zj 0
  • Some errors while reproducing

    Some errors while reproducing

    Hi, Thank you so much for sharing your code. I run the repository on my personal computer however on remote cluster GPU when I have uploaded and tried my code I am facing the following error ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1091)

    urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1091)> I think this is because of comet

    I really want to generate graphs for ImageNet using GPUS.

    opened by manza-ari 0
Owner
Zeyad Emam
PhD student in Applied Mathematics at the University of Maryland - College Park and Pre-doctoral IRTA fellow at NIH.
Zeyad Emam
GitHub
Code for the paper "A Study of Face Obfuscation in ImageNet"

A Study of Face Obfuscation in ImageNet Code for the paper: A Study of Face Obfuscation in ImageNet Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng,

null 35 Oct 4, 2022
Code of PVTv2 is released! PVTv2 largely improves PVTv1 and works better than Swin Transformer with ImageNet-1K pre-training.

Updates (2020/06/21) Code of PVTv2 is released! PVTv2 largely improves PVTv1 and works better than Swin Transformer with ImageNet-1K pre-training. Pyr

null 1.3k Jan 4, 2023
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

This is the Vowpal Wabbit fast online learning code. Why Vowpal Wabbit? Vowpal Wabbit is a machine learning system which pushes the frontier of machin

Vowpal Wabbit 8.1k Jan 6, 2023
A PyTorch re-implementation of the paper 'Exploring Simple Siamese Representation Learning'. Reproduced the 67.8% Top1 Acc on ImageNet.

Exploring simple siamese representation learning This is a PyTorch re-implementation of the SimSiam paper on ImageNet dataset. The results match that

Taojiannan Yang 72 Nov 9, 2022
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection, CVPR 2021. Installation A Linux pla

Tianning Yuan 269 Dec 21, 2022
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021

MI-AOD Language: 简体中文 | English Introduction This is the code for Multiple Instance Active Learning for Object Detection (The PDF is not available tem

Tianning Yuan 269 Dec 21, 2022
Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision https://arxiv.org/abs/2003.00393 Abstract Active learning (AL) aims to min

Denis 29 Nov 21, 2022
Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

Active Learning with the Nvidia TLT Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT). In this tutorial, we will show you ho

Lightly 25 Dec 3, 2022
[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective [PDF] Wuyang Chen, Xinyu Gong, Zhangyang Wang In ICLR 2

VITA 156 Nov 28, 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）

null 51 Dec 1, 2022