Image Retrieval with a Bayesian Model of Relevance Feedback
This work addresses the challenge of improving image retrieval efficiency for users through interactive feedback, but it appears incremental as it builds on existing relevance feedback methods.
The paper tackles the problem of interactive image retrieval by proposing a content-based system that uses multinomial relevance feedback and models user selections with Dirichlet and Beta distributions to balance exploration and exploitation. The new approach shows favorable performance compared to previous work.
A content-based image retrieval system based on multinomial relevance feedback is proposed. The system relies on an interactive search paradigm where at each round a user is presented with k images and selects the one closest to their ideal target. Two approaches, one based on the Dirichlet distribution and one based the Beta distribution, are used to model the problem motivating an algorithm that trades exploration and exploitation in presenting the images in each round. Experimental results show that the new approach compares favourably with previous work.