mlsanityData to 14 Oct 2026

Active Learning via Classifier Impact and Greedy Selection for Interactive Image Retrieval

arXiv 2412.02310 ↗First posted 3 Dec 2024cs.CV cs.IRcited by 5

Not on the map. Why?

Abstract (arXiv)

Active Learning (AL) is a user-interactive approach aimed at reducing annotation costs by selecting the most crucial examples to label. Although AL has been extensively studied for image classification tasks, the specific scenario of interactive image retrieval has received relatively little attention. This scenario presents unique characteristics, including an open-set and class-imbalanced binary classification, starting with very few labeled samples. We introduce a novel batch-mode Active Learning framework named GAL (Greedy Active Learning) that better copes with this application. It incorporates a new acquisition function for sample selection that measures the impact of each unlabeled sample on the classifier. We further embed this strategy in a greedy selection approach, better exploiting the samples within each batch. We evaluate our framework with both linear (SVM) and non-linear MLP/Gaussian Process classifiers. For the Gaussian Process case, we show a theoretical guarantee on the greedy approximation. Finally, we assess our performance for the interactive content-based image retrieval task on several benchmarks and demonstrate its superiority over existing approaches and common baselines. Code is available at https://github.com/barleah/GreedyAL.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 61 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

27 of 61 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  3. 2021ImageNet-21K Pretraining for the Massescited by 613
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  5. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  6. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  7. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  8. 2020Contextual Diversity for Active Learningcited by 139
  9. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  10. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  11. 2021Batch Active Learning at Scalecited by 127
  12. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
15 more
  1. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  2. 2022Active Learning Through a Covering Lenscited by 66
  3. 2022Active Learning by Feature Mixingcited by 63
  4. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  5. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  6. 2022Active Learning for Open-set Annotationcited by 34
  7. 2021Active Learning at the ImageNet Scalecited by 28
  8. 2021Boosting Active Learning via Improving Test Performancecited by 19
  9. 2020On Initial Pools for Deep Active Learningcited by 18
  10. 2019MaxiMin Active Learning in Overparameterized Model Classes}cited by 10
  11. 2020Content-based Image Retrieval and the Semantic Gap in the Deep Learning Eracited by 9
  12. 2021Towards General and Efficient Active Learningcited by 6
  13. 2018Information-Theoretic Active Learning for Content-Based Image Retrievalcited by 5
  14. 2018Fast Interactive Image Retrieval using large-scale unlabeled datacited by 2
  15. 2023Advancing Image Retrieval with Few-Shot Learning and Relevance Feedbackcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Training-Free Active Learning Framework in Materials Science with Large Language Modelscited by 3
  2. 2026Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categoriescited by 2
  3. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0
  4. 2026Foundation-Assisted Active Learning for Object Detection Annotationcited by 0
  5. 2026FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discoverycited by 0