Source code for Task-Aware Variational Adversarial Active Learning

Related tags

Deep Learning TA-VAAL
Overview

Task-Aware Variational Adversarial Active Learning - Official Pytorch implementation of the CVPR 2021 paper

Kwanyoung Kim, Dongwon Park, Kwang In Kim, Se Young Chun

Official Pytorch implementation for the paper presented on CVPR 2021 titled "Task-Aware Variational Adversarial Active Learning".

Network

Abstract

We propose task-aware variational adversarial AL (TA-VAAL) that modifies task-agnostic VAAL, that considered data distribution of both label and unlabeled pools, by relaxing task learning loss prediction to ranking loss prediction and by using ranking conditional generative adversarial network to embed normalized ranking loss information on VAAL. Our proposed TA-VAAL outperforms state-of-the-arts on various benchmark datasets for classifications with balanced / imbalanced labels as well as semantic segmentation and its task-aware and task-agnostic AL properties were confirmed with our in-depth analyses.

Prerequisites:

  • Linux or macOS
  • Python 3.5/3.6
  • CPU compatible but NVIDIA GPU + CUDA CuDNN is highly recommended.
  • pytorch 0.4.1
  • cuda 8.0
  • Anaconda3

Requirements

To install virtual enviornment for requirements:

conda env create -f TAVAAL.yaml

📋 if you already conda, you can activate virtual experiment settings

To activate virtual enviornment:

conda activate TAVAAL

Running code

To train the model(s) and evaluate in the paper, run this command:

python main.py -m TA-VAAL -d cifar10 -c 5 # Other available datasets cifar100, fashionmnist, svhn

if you want to experiment about cifar_imbal. you can run this command:

python main.py  -d cifar10 cifar10im
You might also like...
Based on the paper
Based on the paper "Geometry-aware Instance-reweighted Adversarial Training" ICLR 2021 oral

Geometry-aware Instance-reweighted Adversarial Training This repository provides codes for Geometry-aware Instance-reweighted Adversarial Training (ht

Jingfeng 47 Dec 22, 2022
Ï€-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

Ï€-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis Project Page | Paper | Data Eric Ryan Chan*, Marco Monteiro*, Pe

null 375 Dec 31, 2022
Digan - Official PyTorch implementation of Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Digan - Official PyTorch implementation of Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

DIGAN (ICLR 2022) Official PyTorch implementation of "Generating Videos with Dyn

Sihyun Yu 147 Dec 31, 2022
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis Multi-View Consistent Generative Adversarial Networks for 3D-aware

Xuanmeng Zhang 78 Dec 10, 2022
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021
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
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
Code for Active Learning at The ImageNet Scale.

Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training with torch's DDP.

Zeyad Emam 47 Dec 12, 2022
Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).
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
Comments
  • Missing VAAL experiment and confusing IF condition

    Missing VAAL experiment and confusing IF condition

    Hello,

    I was going through the repository and I noticed that the VAAL experiment is technically isn't present in the code even though the 'VAAL' method is mentioned in the methods in the main.py file.

    methods = ['Random', 'UncertainGCN', 'CoreGCN', 'CoreSet', 'lloss','VAAL','TA-VAAL']

    This conclusion I'm inferring as I saw the train_test.py file and selection_methods.py files and their is no mention of the VAAL experiment.

    Also,

    there is a confusioning if statement written multiple times in the repository, I'm not sure if this is done purposely or by mistake. The statement is:

    if method =='lloss' or 'TA-VAAL':

    This if condition is actually always True, since we are evaluating if method variable contains the string 'lloss' OR the string 'TAVAAL' is None and since 'TAVAAL' is not None, hence the if condition is always true which beats the original purpose of writing the if condition.

    Direct me to clear this issues!

    opened by Prithviraj-prk 0
  • How to run TA-VAAL on Cityscapes?

    How to run TA-VAAL on Cityscapes?

    Hi, thanks for your work. However, this code seems to be only available on classification datasets. How can I run TOD on Cityscapes (or other semantic segmentation datasets) ?

    opened by Haochen-Wang409 0
  • Some source files are missing?

    Some source files are missing?

    Hi,

    Thank you for the interesting work.

    However, when I try to run your code I get the following error

    ImportError: No module named 'models'

    I believe it is because some of the source files are missing in the repository, or have I missed anything?

    Could you please clarify this?

    Thank you in advance.

    opened by sandareka 0
Owner
null
GitHub
Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview)

Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical V

LBK 20 Dec 2, 2022
This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams.

Mutli-agent task allocation This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams. To change

Biorobotics Lab 5 Oct 12, 2022
Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

?? Depth-Aware Generative Adversarial Network for Talking Head Video Generation (CVPR 2022) ?? If DaGAN is helpful in your photos/projects, please hel

Fa-Ting Hong 503 Jan 4, 2023
Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

STARS Laboratory 8 Sep 14, 2022
Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Adversarial Training Against Location-Optimized Adversarial Patches arXiv | Paper | Code | Video | Slides Code for the paper: Sukrut Rao, David Stutz,

Sukrut Rao 32 Dec 13, 2022
Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training

Super-Fast-Adversarial-Training This is a PyTorch Implementation code for develo

LBK 26 Dec 2, 2022
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
Source code of the paper Meta-learning with an Adaptive Task Scheduler.

ATS About Source code of the paper Meta-learning with an Adaptive Task Scheduler. If you find this repository useful in your research, please cite the

Huaxiu Yao 16 Dec 26, 2022
Empower Sequence Labeling with Task-Aware Language Model

LM-LSTM-CRF Check Our New NER Toolkit ?? ?? ?? Inference: LightNER: inference w. models pre-trained / trained w. any following tools, efficiently. Tra

Liyuan Liu 838 Jan 5, 2023
Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)

DialogBERT This is a PyTorch implementation of the DialogBERT model described in DialogBERT: Neural Response Generation via Hierarchical BERT with Dis

Xiaodong Gu 67 Jan 6, 2023