Brief Introduction
- Indicate the "essential difference" between anchor-based and anchor-free detectors
- Propose an "adaptive training sample selection" to automatically select positive and negative training samples
- Demonstrate tiling multiple anchors per location is useless
- Achieve SOTA performance on MS COCO without overhead
Recent vision models
anchor-based & anchor-free
- Mainly two methods for vision processing
Anchor-based
- Double-stage: Faster R-CNN
- Single-stage: Single Shot Detection (SSD)
Anchor-free
- Keypoint-based method: CornerNet
- Center-based method: YOLO
Difference Analysis between two
- RetinaNet (anchor-based) vs. FCOS (anchor-free)
- Attention points
- Dataset: MS COCO (80 object classes)
- RetinaNet (#A=1) → one square anchor box per location
Inconsistency removal
