Research Article
An Evaluation of Deep Learning Methods for Small Object Detection
Figure 2
The visualization of detectors with the strongest backbones on subsets of PASCAL, VOC_MRA_0.58, VOC_MRA_10, VOC_MRA_20, and VOC_WH_20 in order, respectively: (a) YOLO Darknet-53; (b) Faster RCNN ResNeXT-101-64 × 4d-FPN; (c) RetinaNet ResNeXT-101-64 × 4d-FPN; (d) Fast RCNN ResNeXT-101-64 × 4d-FPN.
(a) |
(b) |
(c) |
(d) |