Gallery Filter Network for Person Search

24 Oct 2022  ·  Lucas Jaffe, Avideh Zakhor ·

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.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Person Search CUHK-SYSU SeqNeXt+GFN MAP 96.4 # 1
Top-1 97.0 # 1
Person Search CUHK-SYSU SeqNeXt MAP 96.1 # 2
Top-1 96.5 # 2
Person Search PRW SeqNeXt mAP 57.6 # 2
Top-1 89.5 # 1