Gallery Filter Network for Person Search
This work addresses computational efficiency and accuracy in person search, a domain-specific task for surveillance and security applications, with incremental improvements over existing methods.
The paper tackles the problem of reducing computational cost in person search by introducing the Gallery Filter Network (GFN) to efficiently discard unlikely gallery scenes, and develops the SeqNeXt model to improve person search performance. It demonstrates significant gains over state-of-the-art methods on standard datasets like PRW and CUHK-SYSU.
In person search, we aim to localize a query person from one scene in other gallery scenes. The cost of this search operation is dependent on the number of gallery scenes, making it beneficial to reduce the pool of likely scenes. We describe and demonstrate the Gallery Filter Network (GFN), a novel module which can efficiently discard gallery scenes from the search process, and benefit scoring for persons detected in remaining scenes. We show that the GFN is robust under a range of different conditions by testing on different retrieval sets, including cross-camera, occluded, and low-resolution scenarios. In addition, we develop the base SeqNeXt person search model, which improves and simplifies the original SeqNet model. We show that the SeqNeXt+GFN combination yields significant performance gains over other state-of-the-art methods on the standard PRW and CUHK-SYSU person search datasets. To aid experimentation for this and other models, we provide standardized tooling for the data processing and evaluation pipeline typically used for person search research.