Deep Active Learning

Deep active learning (DAL) aims to train high-performing deep learning models using significantly fewer labeled examples than traditional methods by strategically selecting the most informative data points for human annotation. Current research focuses on developing novel query strategies, often incorporating uncertainty measures and diversity considerations, and adapting these strategies to various model architectures, including convolutional neural networks and transformers, across diverse applications like image classification, object detection, and natural language processing. The effectiveness of DAL is being rigorously evaluated, with a growing emphasis on addressing challenges like class imbalance, label noise, and computational scalability, ultimately aiming to reduce the high cost and time associated with data annotation in many fields.

Papers

November 10, 2024

Deep Active Learning in the Open World
Tian Xie, Jifan Zhang, Haoyue Bai, Robert Nowak
Active Learning Open World Model Adaptation Deep Active Learning

October 21, 2024

Deep Active Learning with Manifold-preserving Trajectory Sampling
Yingrui Ji, Vijaya Sindhoori Kaza, Nishanth Artham, Tianyang Wang
Active Learning Unlabeled Data Annotation Rather Deep Active Learning Trajectory Sampling Labeling Effort Non Image Data

September 27, 2024

AL-GTD: Deep Active Learning for Gaze Target Detection
Francesco Tonini, Nicola Dall'Asen, Lorenzo Vaquero, Cigdem Beyan, Elisa Ricci
Active Learning Deep Active Learning Target Detection Data Sampling Gaze Target Detection

July 1, 2024

DCoM: Active Learning for All Learners
Inbal Mishal, Daphna Weinshall
LeArning Abstract Active Learning Deep Model Deep Active Learning Margin Based Coverage Control Novel Active Learning

June 26, 2024

Towards Deep Active Learning in Avian Bioacoustics
Lukas Rauch, Denis Huseljic, Moritz Wirth, Jens Decke, Bernhard Sick, Christoph Scholz
Deep Learning Model Deep Active Learning Passive Acoustic Monitoring

June 14, 2024

Deep Bayesian Active Learning for Preference Modeling in Large Language Models
Luckeciano C. Melo, Panagiotis Tigas, Alessandro Abate, Yarin Gal
Deep Active Learning Bayesian Active Learning Preference Model Preference Label

May 1, 2024

A Survey on Deep Active Learning: Recent Advances and New Frontiers
Dongyuan Li, Zhen Wang, Yankai Chen, Renhe Jiang, Weiping Ding, Manabu Okumura
Natural Language Processing Timely Survey Active Learning Deep Model Recent Advance New Frontier Deep Active Learning

April 29, 2024

Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagery
Hyunho Lee, Wenwen Li
Inherent Interpretability Deep Active Learning Multi Spectral Satellite Ambiguity Detection Flood Inundation Mapping

April 13, 2024

Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
Denis Huseljic, Paul Hahn, Marek Herde, Lukas Rauch, Bernhard Sick
Deep Neural Network High Efficiency Supervised ImageNet Large Scale Binary Classification Deep Active Learning Efficient Classification ANGLEr Behavior Approximate Sampling

April 6, 2024

ProtoAL: Interpretable Deep Active Learning with prototypes for medical imaging
Iury B. de A. Santos, André C. P. L. F. de Carvalho
Deep Learning Medical Imaging Visual Prototype Deep Active Learning

March 21, 2024

Deep Active Learning: A Reality Check
Edrina Gashi, Jiankang Deng, Ismail Elezi
Deep Learning Deep Learning Model Active Learning Deep Active Learning Reality Check

February 2, 2024

Deep Active Learning for Data Mining from Conflict Text Corpora
Mihai Croicu
Active Learning Human Annotation Data Mining Event Data Deep Active Learning Armed Conflict Conflict Dynamic

January 28, 2024

A Study of Acquisition Functions for Medical Imaging Deep Active Learning
Bonaventure F. P. Dossou
Active Learning Study Feature Deep Learning Algorithm Deep Active Learning Breast Cancer Detection Acquisition Function Melanoma Detection AI Revolution

January 18, 2024

Querying Easily Flip-flopped Samples for Deep Active Learning
Seong Jin Cho, Gwangsu Kim, Junghyun Lee, Jinwoo Shin, Chang D. Yoo
Active Learning Query Information Predictive Uncertainty External Sample Decision Boundary Deep Active Learning Active Learning Algorithm Based Active Learning

January 15, 2024

Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification
Wei Tan, Ngoc Dang Nguyen, Lan Du, Wray Buntine
Natural Language Processing Real Power Deep Active Learning Multi Label Text Classification

January 9, 2024

Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions
Andreas Kirsch
Deep Learning Active Learning General Principle Deep Active Learning Active Sampling Label Efficiency Data Subset Selection Information Theoretical

December 14, 2023

DIRECT: Deep Active Learning under Imbalance and Label Noise
Shyam Nuggehalli, Jifan Zhang, Lalit Jain, Robert Nowak
Active Learning Label Noise Deep Active Learning Group Imbalance Active Learning Algorithm Class Separation

December 10, 2023

Benchmarking of Query Strategies: Towards Future Deep Active Learning
Shiryu Ueno, Yusei Yamada, Shunsuke Nakatsuka, Kunihito Kato
Benchmark Platform MNIST Dataset Deep Active Learning Query Strategy

November 27, 2023

Leveraging deep active learning to identify low-resource mobility functioning information in public clinical notes
Tuan-Dung Le, Zhuqi Miao, Samuel Alvarado, Brittany Smith, William Paiva, Thanh Thieu
BERT Model Human Annotation Clinical Note Full Information Annotated Dataset Deep Active Learning Resource Constrained Device Clinical Natural Language Processing Clinical Natural Language Processing Task

October 22, 2023

A comprehensive survey on deep active learning in medical image analysis
Haoran Wang, Qiuye Jin, Shiman Li, Siyu Liu, Manning Wang, Zhijian Song
Active Learning Medical Image Comprehensive Survey Medical Image Analysis Deep Active Learning