Analysis of Visual Reasoning on One-Stage Object Detection
This addresses a limitation in object detection for computer vision applications, but it is incremental as it builds on existing YOLOv3 with enhancements.
The paper tackled the problem of one-stage object detectors ignoring object relations by analyzing reasoning features with self-attention architectures, resulting in the YOLOv3-Reasoner2 model achieving a 2.5% absolute mAP improvement on COCO while maintaining real-time performance.
Current state-of-the-art one-stage object detectors are limited by treating each image region separately without considering possible relations of the objects. This causes dependency solely on high-quality convolutional feature representations for detecting objects successfully. However, this may not be possible sometimes due to some challenging conditions. In this paper, the usage of reasoning features on one-stage object detection is analyzed. We attempted different architectures that reason the relations of the image regions by using self-attention. YOLOv3-Reasoner2 model spatially and semantically enhances features in the reasoning layer and fuses them with the original convolutional features to improve performance. The YOLOv3-Reasoner2 model achieves around 2.5% absolute improvement with respect to baseline YOLOv3 on COCO in terms of mAP while still running in real-time.