Transcription of FCOS: Fully Convolutional One-Stage Object Detection
{{id}} {{{paragraph}}}
FCOS: Fully Convolutional One-Stage Object DetectionZhi TianChunhua Shen Hao ChenTong HeThe University of Adelaide, AustraliaAbstractWe propose a Fully Convolutional One-Stage Object detec-tor (FCOS) to solve Object Detection in a per-pixel predic-tion fashion, analogue to semantic segmentation. Almostall state-of-the-art Object detectors such as RetinaNet, SSD,YOLOv3, and Faster R-CNN rely on pre-defined anchorboxes. In contrast, our proposed detector FCOS is anchorbox free, as well as proposal free. By eliminating the pre-defined set of anchor boxes, FCOS completely avoids thecomplicated computation related to anchor boxes such ascalculating overlapping during training.
CornerNet [13] is a recently proposed one-stage anchor-free detector, which detects a pair of corners of a bound-ing box and groups them to form the final detected bound-ing box. CornerNet requires much more complicated post-processing to group the pairs of corners belonging to the same instance. An extra distance metric is learned for the
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}