Dive Deeper Into Box for Object Detection
This addresses localization errors in object detection for computer vision applications, representing an incremental improvement.
The paper tackles inaccurate bounding box localization in anchor-free object detection by proposing DDBNet, a box reorganization method that filters drifted boxes and regroups well-aligned boundaries, achieving state-of-the-art performance.
Anchor free methods have defined the new frontier in state-of-the-art object detection researches where accurate bounding box estimation is the key to the success of these methods. However, even the bounding box has the highest confidence score, it is still far from perfect at localization. To this end, we propose a box reorganization method(DDBNet), which can dive deeper into the box for more accurate localization. At the first step, drifted boxes are filtered out because the contents in these boxes are inconsistent with target semantics. Next, the selected boxes are broken into boundaries, and the well-aligned boundaries are searched and grouped into a sort of optimal boxes toward tightening instances more precisely. Experimental results show that our method is effective which leads to state-of-the-art performance for object detection.