Distilling object detectors with efficient logit mimicking and mask-guided feature imitation

Xin Lu, Yichao Cao, Shikun Chen, Weixuan Li, Xin Zhou, Xiaobo Lu

Abstract

Highlights•Distillation via classification logits can benefit one-class object detection.•Logit mimicking for localization mitigates missed and false detections.•Teacher sample selection enhances knowledge transmission efficiency.•A soft metric and a loss-guided mask are more suitable for feature imitation.
BibTeX
@article{lu2024distilling,
  author = {Xin Lu and Yichao Cao and Shikun Chen and Weixuan Li and Xin Zhou and Xiaobo Lu},
  title = {{Distilling object detectors with efficient logit mimicking and mask-guided feature imitation}},
  journal = {Expert Systems with Applications},
  year = {2024},
  doi = {10.1016/j.eswa.2023.123079},
}

Loading related content...

Figure