Corpus ID: 209500865

Combining Deep Learning and Verification for Precise Object Instance Detection

@inproceedings{Ancha2019CombiningDL,
  title={Combining Deep Learning and Verification for Precise Object Instance Detection},
  author={Siddharth Ancha and Junyu Nan and David Held},
  booktitle={CoRL},
  year={2019}
}
Deep learning object detectors often return false positives with very high confidence. Although they optimize generic detection performance, such as mean average precision (mAP), they are not designed for reliability. For a reliable detection system, if a high confidence detection is made, we would want high certainty that the object has indeed been detected. To achieve this, we have developed a set of verification tests which a proposed detection must pass to be accepted. We develop a… Expand
A Multi-target Edge Service Approach to Real-time Image Object Detection

References

SHOWING 1-10 OF 57 REFERENCES
Target Driven Instance Detection
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
Robust single-view instance recognition
Multimodal blending for high-accuracy instance recognition
Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
Safety Verification of Deep Neural Networks
SSD: Single Shot MultiBox Detector
Gradient Response Maps for Real-Time Detection of Textureless Objects
A dataset for developing and benchmarking active vision
...
1
2
3
4
5
...