DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval
This addresses the problem of more controllable and fault-tolerant image retrieval for users in interactive settings, though it appears incremental as it builds on existing retrieval methods with a novel dialog-based approach.
The paper tackles interactive, conversational text-to-image retrieval by proposing the DIR-TIR framework, which uses dialog and image refinement modules to improve target image hit accuracy, outperforming single-query baselines in experiments.
This paper addresses the task of interactive, conversational text-to-image retrieval. Our DIR-TIR framework progressively refines the target image search through two specialized modules: the Dialog Refiner Module and the Image Refiner Module. The Dialog Refiner actively queries users to extract essential information and generate increasingly precise descriptions of the target image. Complementarily, the Image Refiner identifies perceptual gaps between generated images and user intentions, strategically reducing the visual-semantic discrepancy. By leveraging multi-turn dialogues, DIR-TIR provides superior controllability and fault tolerance compared to conventional single-query methods, significantly improving target image hit accuracy. Comprehensive experiments across diverse image datasets demonstrate our dialogue-based approach substantially outperforms initial-description-only baselines, while the synergistic module integration achieves both higher retrieval precision and enhanced interactive experience.