Object Detection Models
TridentNet
Introduced by Li et al. in Scale-Aware Trident Networks for Object DetectionTridentNet is an object detection architecture that aims to generate scale-specific feature maps with a uniform representational power. A parallel multi-branch architecture is constructed in which each branch shares the same transformation parameters but with different receptive fields. A scale-aware training scheme is used to specialize each branch by sampling object instances of proper scales for training.
Source: Scale-Aware Trident Networks for Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Soft-NMS
TridentNet Block
