Dual Refinement Network for Single-Shot Object Detection

@article{Chen2019DualRN,
  title={Dual Refinement Network for Single-Shot Object Detection},
  author={Xingyu Chen and Zhengxing Wu and Junzhi Yu},
  journal={2019 International Conference on Robotics and Automation (ICRA)},
  year={2019},
  pages={8305-8310}
}
Object detection methods fall into two categories, i.e., two-stage and single-stage detectors. The former is characterized by high detection accuracy while the latter usually has a considerable inference speed. Hence, it is imperative to fuse their merits for a better accuracy vs. speed trade-off. To this end, we propose a dual refinement network (DRN) to boost the performance of the single-stage detector. Inheriting from the advantages of two-stage approaches (i.e., two-step regression and… Expand
9 Citations
RefineDet++: Single-Shot Refinement Neural Network for Object Detection
  • 3
Auxiliary Detection Head for One-Stage Object Detection
  • PDF
VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results
  • 35
  • PDF
RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation
  • 2
  • PDF
Reveal of Domain Effect: How Visual Restoration Contributes to Object Detection in Aquatic Scenes
  • 3
  • PDF
Continuity, Stability, and Integration: Novel Tracking-Based Perspectives for Temporal Object Detection
  • PDF
Rethinking Temporal Object Detection from Robotic Perspectives
  • 1

References

SHOWING 1-10 OF 66 REFERENCES
Single-Shot Refinement Neural Network for Object Detection
  • 582
  • Highly Influential
  • PDF
Flow-Guided Feature Aggregation for Video Object Detection
  • 265
  • Highly Influential
  • PDF
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
  • 13,428
  • PDF
You Only Look Once: Unified, Real-Time Object Detection
  • 11,381
  • PDF
Object Detection With Deep Learning: A Review
  • 862
  • Highly Influential
  • PDF
Detect to Track and Track to Detect
  • 257
  • PDF
SSD: Single Shot MultiBox Detector
  • 10,642
  • Highly Influential
  • PDF
Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
  • 13
  • PDF
RON: Reverse Connection with Objectness Prior Networks for Object Detection
  • 260
  • PDF
...
1
2
3
4
5
...