Information-theoretic Active Learning For Content-based Image Retrieval

Abstract

We propose Information-Theoretic Active Learning (ITAL), a novel batch-mode active learning method for binary classification, and apply it for acquiring meaningful user feedback in the context of content-based image retrieval. Instead of combining different heuristics such as uncertainty, diversity, or density, our method is based on maximizing the mutual information between the predicted relevance of the images and the expected user feedback regarding the selected batch. We propose suitable approximations to this computationally demanding problem and also integrate an explicit model of user behavior that accounts for possible incorrect labels and unnameable instances. Furthermore, our approach does not only take the structure of the data but also the expected model output change caused by the user feedback into account. In contrast to other methods, ITAL turns out to be highly flexible and provides state-of-the-art performance across various datasets, such as MIRFLICKR and ImageNet.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keybarz2018information

Related papers

• Active Learning Via Classifier Impact And Greedy Selection For Interactive Image Retrieval (2024)0.95
• Fast Interactive Image Retrieval Using Large-scale Unlabeled Data (2018)0.00
• Active Learning For Finely-categorized Image-text Retrieval By Selecting Hard Negative Unpaired Samples (2024)2.26
• 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
• Advancing Image Retrieval With Few-shot Learning And Relevance Feedback (2023)0.00
• Revisiting Relevance Feedback For Clip-based Interactive Image Retrieval (2024)4.52
• Give Me A Hint! Navigating Image Databases Using Human-in-the-loop Feedback (2018)7.16