Thread by @ai_fast_track

CornerNet Follow-up Paper- CenterNet: Keypoint Triplets for Object Detection
🧵
- CornerNet focus on detecting object edges leads to generating boxes sharing similar edges👇

- 🔥CenterNet Solution🔥: It adds a Center Pooling

- Objects central parts have richer features (map) than corner regions (those rely on Corner Pooling to compensate features lack). CenterNet correctly detects objects by checking the central parts, in addition to their corners.

Performance Comparison: CenterNet ranks among the top SOTA Two-Stage Detectors.

The CenterNet Architecture might explain why the FCOS authors chose to predict an inner (center) point plus all the distances to the left, right, top, and bottom edges: The inner point has richer information (features map). Plus, they use a Center Branch to improve accuracy

You can find my FCOS presentation slides (shown 👆) in the segmentation channel (Pinned Message) in our forum.

Forum: discord.gg/JDBeZYK
# segmentation

Paper: arxiv.org/pdf/1904.08189…