Active Learning Via Classifier Impact And Greedy Selection For Interactive Image Retrieval

Abstract

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

Stats

• citations0
• S2 citations—
• github stars2
• HF likes0
• heat score0.95
• arxiv keybar2024active

Related papers

• Fast Interactive Image Retrieval Using Large-scale Unlabeled Data (2018)0.00
• Information-theoretic Active Learning For Content-based Image Retrieval (2018)5.24
• Annotation Cost Efficient Active Learning For Content Based Image Retrieval (2023)5.84
• Active Learning For Fine-grained Sketch-based Image Retrieval (2023)0.00
• Dialog-based Interactive Image Retrieval (2018)0.00
• Annotation Cost-efficient Active Learning For Deep Metric Learning Driven Remote Sensing Image Retrieval (2024)3.58
• Active Learning For Finely-categorized Image-text Retrieval By Selecting Hard Negative Unpaired Samples (2024)2.26
• Revisiting Relevance Feedback For Clip-based Interactive Image Retrieval (2024)4.52