Distilling Image Classifiers in Object DetectorsDownload PDF

21 May 2021, 20:47 (edited 27 Jan 2022)NeurIPS 2021 PosterReaders: Everyone
  • Keywords: knowledge distillation, classifier-to-detector, across tasks, object detection
  • TL;DR: We introduce a classifier-to-detector distillation framework to transfer knowledge across both architectures and tasks, improving the performance of compact student detectors.
  • Abstract: Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains limited to the scenario where the student and the teacher tackle the same task. Here, we investigate the problem of transferring knowledge not only across architectures but also across tasks. To this end, we study the case of object detection and, instead of following the standard detector-to-detector distillation approach, introduce a classifier-to-detector knowledge transfer framework. In particular, we propose strategies to exploit the classification teacher to improve both the detector's recognition accuracy and localization performance. Our experiments on several detectors with different backbones demonstrate the effectiveness of our approach, allowing us to outperform the state-of-the-art detector-to-detector distillation methods.
  • Supplementary Material: pdf
  • Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
  • Code: https://github.com/NVlabs/DICOD
13 Replies