Active Learning

Active learning is a machine learning paradigm focused on optimizing data labeling efficiency by strategically selecting the most informative samples for annotation from a larger unlabeled pool. Current research emphasizes developing novel acquisition functions and data pruning strategies to reduce computational costs associated with large datasets, exploring the integration of active learning with various model architectures (including deep neural networks, Gaussian processes, and language models), and addressing challenges like privacy preservation and handling open-set noise. This approach holds significant promise for reducing the substantial cost and effort of data labeling in diverse fields, ranging from image classification and natural language processing to materials science and healthcare.

Papers

June 21, 2023

June 19, 2023

June 16, 2023

ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
Lukas Rauch, Matthias Aßenmacher, Denis Huseljic, Moritz Wirth, Bernd Bischl, Bernhard Sick
New Benchmark Transformer Megatron Decepticons Active Learning Transformer Based Language Model Deep Active Learning Annotation Cost

June 15, 2023

Re-Benchmarking Pool-Based Active Learning for Binary Classification
Po-Yi Lu, Chun-Liang Li, Hsuan-Tien Lin
Active Learning Binary Classification

June 13, 2023

A Markovian Formalism for Active Querying
Sid Ijju
Active Learning Active Learning Algorithm

June 12, 2023

Active Learning Guided Fine-Tuning for enhancing Self-Supervised Based Multi-Label Classification of Remote Sensing Images
Lars Möllenbrok, Begüm Demir
Self Supervised Active Learning Multi Label Remote Sensing Image Multi Label Classification Self Supervised Pre Training Active Finetuning

June 9, 2023

Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach
Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Xingchen Wan, Vu Nguyen, Harald Oberhauser, Michael A. Osborne
Active Learning Bayesian Optimization Constrained Learning Front Diverse Batch

June 7, 2023

June 6, 2023

June 5, 2023

Deep Active Learning with Structured Neural Depth Search
Xiaoyun Zhang, Xieyi Ping, Jianwei Zhang
Active Learning Neural Architecture Search Depth Network Deep Active Learning

June 2, 2023

Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification
Nathan Beck, Krishnateja Killamsetty, Suraj Kothawade, Rishabh Iyer
Active Learning Online Learning Verification Task Language Correction Human Interaction Instance Level Label

June 1, 2023

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions
Ben Adcock, Juan M. Cardenas, Nick Dexter
Active Learning General Framework Adaptive Sampling VIS4ML Research Approximation Space Gradient Amplification

May 30, 2023

May 27, 2023

USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution
Vikrant Rangnekar, Uddeshya Upadhyay, Zeynep Akata, Biplab Banerjee
Active Learning Super Resolution High Dimensional Pixel Wise Uncertainty Dense Training

Active Learning

Papers

Multi-Task Consistency for Active Learning

M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

Taming Small-sample Bias in Low-budget Active Learning

Perturbation-Based Two-Stage Multi-Domain Active Learning

ActiveGLAE: A Benchmark for Deep Active Learning with Transformers

Re-Benchmarking Pool-Based Active Learning for Binary Classification

A Markovian Formalism for Active Querying

Active Learning Guided Fine-Tuning for enhancing Self-Supervised Based Multi-Label Classification of Remote Sensing Images

Adaptive Batch Sizes for Active Learning A Probabilistic Numerics Approach

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings (Extended Version)

NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis

Deep Active Learning with Structured Neural Depth Search

Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

Parallelized Acquisition for Active Learning using Monte Carlo Sampling

atTRACTive: Semi-automatic white matter tract segmentation using active learning

USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution