Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback
This work addresses the challenge of navigating image databases for users by enabling more efficient search through visual feedback, though it is incremental as it builds on prior methods like Conditional Similarity Networks.
The paper tackles the problem of interactive image search by introducing an attribute-based system that uses human-in-the-loop feedback to refine results, achieving compelling outcomes on active image search and image attribute representation tasks.
In this paper, we introduce an attribute-based interactive image search which can leverage human-in-the-loop feedback to iteratively refine image search results. We study active image search where human feedback is solicited exclusively in visual form, without using relative attribute annotations used by prior work which are not typically found in many datasets. In order to optimize the image selection strategy, a deep reinforcement model is trained to learn what images are informative rather than rely on hand-crafted measures typically leveraged in prior work. Additionally, we extend the recently introduced Conditional Similarity Network to incorporate global similarity in training visual embeddings, which results in more natural transitions as the user explores the learned similarity embeddings. Our experiments demonstrate the effectiveness of our approach, producing compelling results on both active image search and image attribute representation tasks.