PLOT: Text-based Person Search with Part Slot Attention for Corresponding Part Discovery
This work addresses the problem of part-level alignment in text-based person search for applications like surveillance or retrieval, representing an incremental advance over existing methods.
The paper tackles the challenge of aligning visual and textual representations at the human part level in text-based person search by proposing a framework that uses part discovery with slot attention and dynamic part attention, achieving significant improvements in retrieval accuracy on three public benchmarks.
Text-based person search, employing free-form text queries to identify individuals within a vast image collection, presents a unique challenge in aligning visual and textual representations, particularly at the human part level. Existing methods often struggle with part feature extraction and alignment due to the lack of direct part-level supervision and reliance on heuristic features. We propose a novel framework that leverages a part discovery module based on slot attention to autonomously identify and align distinctive parts across modalities, enhancing interpretability and retrieval accuracy without explicit part-level correspondence supervision. Additionally, text-based dynamic part attention adjusts the importance of each part, further improving retrieval outcomes. Our method is evaluated on three public benchmarks, significantly outperforming existing methods.