Blog
About

0
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      TKD: Temporal Knowledge Distillation for Active Perception

      Preprint

      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to 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 vision 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 networks 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) an Long-short Term Memory (LSTM) based key frame selection method; and 2) a novel teacher-bounded loss design. To validate, 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, compare to other modern object recognition methods.

          Related collections

          Most cited references 10

          • Record: found
          • Abstract: not found
          • Book Chapter: not found

          SSD: Single Shot MultiBox Detector

            Bookmark
            • Record: found
            • Abstract: not found
            • Book Chapter: not found

            XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

                Bookmark

                Author and article information

                Journal
                04 March 2019
                Article
                1903.01522

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                cs.CV

                Computer vision & Pattern recognition

                Comments

                Comment on this article