TKD: Temporal knowledge distillation for active perception

Mohammad Farhadi, Yezhou Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Deep neural network-based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite the significant performance improvement using the deep structures, they still require prohibitive runtime to process images and maintain the highest possible performance for real-time applications. Observing the phenomenon that human visual system (HVS) relies heavily on the temporal dependencies among frames from the visual input to conduct recognition efficiently, we propose a novel framework dubbed as TKD: temporal knowledge distillation. This framework distills the temporal knowledge from a heavy neural network-based model over selected video frames (the perception of the moments) to a light-weight model. To enable the distillation, we put forward two novel procedures: 1) a Long-short Term Memory (LSTM)-based keyframe selection method; and 2) a novel teacher-bounded loss design. To validate our approach, we conduct comprehensive empirical evaluations using different object detection methods over multiple datasets including Youtube-Objects and Hollywood scene dataset. Our results show consistent improvement in accuracy-speed trad- offs for object detection over the frames of the dynamic scene, compared to other modern object recognition methods. It can maintain the desired accuracy with the throughput of around 220 images per second. Implementation: https://github.com/mfarhadi/TKD-Cloud.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages942-951
Number of pages10
ISBN (Electronic)9781728165530
DOIs
StatePublished - Mar 2020
Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
Duration: Mar 1 2020Mar 5 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
CountryUnited States
CitySnowmass Village
Period3/1/203/5/20

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'TKD: Temporal knowledge distillation for active perception'. Together they form a unique fingerprint.

Cite this