ssFPN: Scale Sequence (S^2) Feature Based-Feature Pyramid Network for Object Detection
This addresses the issue of poor detection performance for small objects in computer vision applications, representing an incremental improvement over existing FPN-based methods.
The paper tackled the problem of low average precision (AP) for small objects in object detection by proposing a scale sequence (S^2) feature extraction method for Feature Pyramid Networks (FPN), achieving AP improvements of up to 2.0% on models like Faster R-CNN and Mask R-CNN on the MS COCO dataset.
Feature Pyramid Network (FPN) has been an essential module for object detection models to consider various scales of an object. However, average precision (AP) on small objects is relatively lower than AP on medium and large objects. The reason is why the deeper layer of CNN causes information loss as feature extraction level. We propose a new scale sequence (S^2) feature extraction of FPN to strengthen feature information of small objects. We consider FPN structure as scale-space and extract scale sequence (S^2) feature by 3D convolution on the level axis of FPN. It is basically scale invariant feature and is built on high-resolution pyramid feature map for small objects. Furthermore, the proposed S^2 feature can be extended to most object detection models based on FPN. We demonstrate the proposed S2 feature can improve the performance of both one-stage and two-stage detectors on MS COCO dataset. Based on the proposed S2 feature, we achieve upto 1.3% and 1.1% of AP improvement for YOLOv4-P5 and YOLOv4-P6, respectively. For Faster RCNN and Mask R-CNN, we observe upto 2.0% and 1.6% of AP improvement with the suggested S^2 feature, respectively.