AlignPS, or Feature-Aligned Person Search Network, is an anchor-free framework for efficient person search. The model employs the typical architecture of an anchor-free detection model (i.e., FCOS). An aligned feature aggregation (AFA) module is designed to make the model focus more on the re-id subtask. Specifically, AFA reshapes some building blocks of FPN to overcome the issues of region and scale misalignment in re-id feature learning. A deformable convolution is exploited to make the re-id embeddings adaptively aligned with the foreground regions. A feature fusion scheme is designed to better aggregate features from different FPN levels, which makes the re-id features more robust to scale variations. The training procedures of re-id and detection are also optimized to place more emphasis on generating robust re-id embeddings.
Source: Efficient Person Search: An Anchor-Free ApproachPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
Deformable Convolution
|
Convolutions | |
FCOS
|
Object Detection Models | |
FPN
|
Feature Extractors |