CenterNet is a one-stage object detector that detects each object as a triplet, rather than a pair, of keypoints. It utilizes two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. The intuition is that, if a predicted bounding box has a high IoU with the ground-truth box, then the probability that the center keypoint in its central region is predicted as the same class is high, and vice versa. Thus, during inference, after a proposal is generated as a pair of corner keypoints, we determine if the proposal is indeed an object by checking if there is a center keypoint of the same class falling within its central region.
Source: CenterNet: Keypoint Triplets for Object DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 29 | 34.12% |
Pose Estimation | 5 | 5.88% |
Semantic Segmentation | 3 | 3.53% |
Object Detection In Aerial Images | 2 | 2.35% |
Keypoint Detection | 2 | 2.35% |
Instance Segmentation | 2 | 2.35% |
Super-Resolution | 2 | 2.35% |
Object Tracking | 2 | 2.35% |
Depth Estimation | 2 | 2.35% |
Component | Type |
|
---|---|---|
Cascade Corner Pooling
|
Pooling Operations | |
Center Pooling
|
Pooling Operations | |
DLA
|
Feature Extractors |