Awesome Active Learning

🤩 A curated list of awesome Active Learning ! 🤩

Background

What is Active Learning?

Active learning is a special case of machine learning in which a learning algorithm can interactively query a oracle (or some other information source) to label new data points with the desired outputs.

(image source: Settles, Burr)

There are situations in which unlabeled data is abundant but manual labeling is expensive. In such a scenario, learning algorithms can actively query the oracle for labels. This type of iterative supervised learning is called active learning. Since the learner chooses the examples, the number of examples to learn a concept can often be much lower than the number required in normal supervised learning. With this approach, there is a risk that the algorithm is overwhelmed by uninformative examples. Recent developments are dedicated to multi-label active learning, hybrid active learning and active learning in a single-pass (on-line) context, combining concepts from the field of machine learning (e.g. conflict and ignorance) with adaptive, incremental learning policies in the field of online machine learning.

(source: Wikipedia)

Contributing

If you find the awesome paper/code/book/tutorial or have some suggestions, please feel free to pull requests or contact [email protected] to add papers using the following Markdown format:

Year | Paper Name | Conference | [Paper](link) | [Code](link) | Tags | Notes |

Thanks for your valuable contribution to the research community. 😃

Books
Surveys
Papers
Turtorials
Tools

Books

Active Learning. Burr Settles. (CMU, 2012)

Surveys

Active Learning Literature Survey. Settles, Burr. (2009)
A Survey of Deep Active Learning. Pengzhen Ren et al. (2020)
From Model-driven to Data-driven: A Survey on Active Deep Learning. Peng Liu et al. (2021)

Papers

Before 2017

Year	Title	Conf	Paper
1994	Improving Generalization with Active Learning	Machine Learning	paper
2007	Discriminative Batch Mode Active Learning	NIPS	paper
2008	Active Learning with Direct Query Construction	KDD	paper
2008	An Analysis of Active Learning Strategies for Sequence Labeling Tasks	EMNLP	paper
2008	Hierarchical Sampling for Active Learning	ICML	paper
2010	Active Instance Sampling via Matrix Partition	NIPS	paper
2011	Ask Me Better Questions: Active Learning Queries Based on Rule Induction	KDD	paper
2011	Active Learning from Crowds	ICML	paper
2011	Bayesian Active Learning for Classification and Preference Learning	CoRR	paper
2011	Active Learning Using On-line Algorithms	KDD	paper
2012	Bayesian Optimal Active Search and Surveying	ICML	paper
2012	Batch Active Learning via Coordinated Matching	ICML	paper
2013	Active Learning for Multi-Objective Optimization	ICML	paper
2013	Active Learning for Probabilistic Hypotheses Usingthe Maximum Gibbs Error Criterion	NIPS	paper
2014	Active Semi-Supervised Learning Using Sampling Theory for Graph Signals	KDD	paper
2014	Beyond Disagreement-based Agnostic Active Learning	NIPS	paper
2016	Cost-Effective Active Learning for Deep Image Classification	TCSVT	paper
2016	Active Image Segmentation Propagation	CVPR	paper

2017

Title	Conf	Paper	Code	Tags
Active Decision Boundary Annotation with Deep Generative Models	ICCV	paper
Active One-shot Learning	CoRR	paper	code	`Str.` `RL.` `FS.`
A Meta-Learning Approach to One-Step Active-Learning	[email protected]/ECML	paper		`Pool.` `Meta.`
Generative Adversarial Active Learning	arXiv	paper		`Pool.` `Syn.`
Active Learning from Peers	NIPS	paper
Learning Active Learning from Data	NIPS	paper	code	`Pool.`
Learning Algorithms for Active Learning	ICML	paper
Deep Bayesian Active Learning with Image Data	ICML	paper	code	`Pool.`

2018

Title	Conf	Paper	Code	Tags
The Power of Ensembles for Active Learning in Image Classification	CVPR	paper
Adversarial Learning for Semi-Supervised Semantic Segmentation	BMVC	paper	code	`Pool.` `SSL.`
A Variance Maximization Criterion for Active Learning	Pattern Recognition	paper
Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning	ICLR-WS	paper		`Pool.` `Meta.` `RL.`
Active Learning for Convolutional Neural Networks: A Core-Set Approach	ICLR	paper
Adversarial Active Learning for Sequence Labeling and Generation	IJCAI	paper
Meta-Learning for Batch Mode Active Learning	ICLR-WS	paper

2019

Title	Conf	Paper	Code	Tags
ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation	CVPR	paper		`Pool.`
Bayesian Generative Active Deep Learning	ICML	paper	code	`Pool.` `Semi.`
Variational Adversarial Active Learning	ICCV	paper	code	`Pool.` `SSL.`
Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning	NeurIPS	paper
Active Learning via Membership Query Synthesisfor Semi-supervised Sentence Classification	CoNLL	paper
Discriminative Active Learning	arXiv	paper
Semantic Redundancies in Image-Classification Datasets: The 10% You Don’t Need	arXiv	paper
Bayesian Batch Active Learning as Sparse Subset Approximation	NIPS	paper
Learning Loss for Active Learning	CVPR	paper	code	`Pool.`
Rapid Performance Gain through Active Model Reuse	IJCAI	paper
Parting with Illusions about Deep Active Learning	arXiv	paper		`Cri.`
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning	NIPS	paper

2020

Title	Conf	Paper	Code	Tags
Reinforced active learning for image segmentation	ICLR	paper	code	`Pool.` `RL.`
[BADGE] Batch Active learning by Diverse Gradient Embeddings	ICLR	paper	code	`Pool.`
Adversarial Sampling for Active Learning	WACV	paper		`Pool.`
Online Active Learning of Reject Option Classifiers	AAAI	paper
Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision	CVPR	paper
Deep Reinforcement Active Learning for Medical Image Classification	MICCAI	paper		`Pool.` `RL.`
State-Relabeling Adversarial Active Learning	CVPR	paper	code	`Pool.`
Towards Robust and Reproducible Active Learning Using Neural Networks	arXiv	paper		`Cri.`
Consistency-Based Semi-supervised Active Learning: Towards Minimizing Labeling Cost	ECCV	paper		`Pool.` `SSL.`

2021

Title	Conf	Paper	Code	Tags	Notes
MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning	arXiv	paper		`Pool.` `Meta.` `RL.`
Can Active Learning Preemptively Mitigate Fairness Issues	ICLR-RAI	paper	code	`Pool.`	Thinking fairness issues
Sequential Graph Convolutional Network for Active Learning	CVPR	paper	code	`Pool.`
Task-Aware Variational Adversarial Active Learning	CVPR	paper	code	`Pool.`
Effective Evaluation of Deep Active Learning on Image Classification Tasks	arXiv	paper		`Cri.`
Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual Labels	ICCV	paper		`Pool.` `SSL.`
Contrastive Coding for Active Learning under Class Distribution Mismatch	ICCV	paper	code	`Pool.`	Defines a good question
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering	ACL-IJCNLP	paper	code	`Pool.`	Thinking about outliers
LADA: Look-Ahead Data Acquisition via Augmentation for Active Learning	NeurIPS	paper		`Pool.`
Multi-Anchor Active Domain Adaptation for Semantic Segmentation	ICCV	paper	code	`Pool.`
Active Learning for Lane Detection: A Knowledge Distillation Approach	ICCV	paper		`Pool.`
Active Contrastive Learning of Audio-Visual Video Representations	ICLR	paper	code	`Pool.`
Multiple instance active learning for object detection	CVPR	paper	code	`Pool.`
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency	NeurIPS	paper			Robot exploration
Influence Selection for Active Learning	ICCV	paper	code	`Pool.`
Reducing Label Effort: Self-Supervised meets Active Learning	arXiv	paper		`Pool.` `SS.` `Cri.`	A meaningful attempt on the combination of SS & AL

Turtorials

Overview of Active Learning for Deep Learning. Jacob Gildenblat.
Active Learning from Theory to Practice. Steve Hanneke, Robert Nowak. (ICML, 2019)

Tools

ALiPy: Active Learning in Python. Ying-Peng Tang, Guo-Xiang Li, Sheng-Jun Huang. (NUAA, 2019)
[BAAL] A Bayesian Active Learning Library. Atighehchian, Parmida and Branchaud-Charron, Frederic and Freyberg, Jan and Pardinas, Rafael and Schell, Lorne. (2019)

A curated list of awesome Active Learning

Related tags

Overview

Awesome Active Learning

Background

What is Active Learning?

Contributing

Table of Contents

Books

Surveys

Papers

Tags

Before 2017

2017

2018

2019

2020

2021

Turtorials

Tools

Owner

BAI Fan

nn_builder lets you build neural networks with less boilerplate code

[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )

CAPITAL: Optimal Subgroup Identification via Constrained Policy Tree Search

Implementation of Vaswani, Ashish, et al. "Attention is all you need."

The codebase for our paper "Generative Occupancy Fields for 3D Surface-Aware Image Synthesis" (NeurIPS 2021)

This is a pytorch implementation for the BST model from Alibaba https://arxiv.org/pdf/1905.06874.pdf

A custom DeepStack model for detecting 16 human actions.

PyTorch implementation of the end-to-end coreference resolution model with different higher-order inference methods.

A script helps the user to update Linux and Mac systems through the terminal

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

LUKE -- Language Understanding with Knowledge-based Embeddings

Author's PyTorch implementation of TD3 for OpenAI gym tasks

UIUCTF 2021 Public Challenge Repository

Codes for the ICCV'21 paper "FREE: Feature Refinement for Generalized Zero-Shot Learning"

Multi-Person Extreme Motion Prediction

Breaking the Dilemma of Medical Image-to-image Translation

YOLOv5 + ROS2 object detection package

Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)

Official implementation of VQ-Diffusion

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators