Tracking-by-Trackers with a Distilled and Reinforced Model
arXiv:2007.04108 · doi:10.1007/978-3-030-69532-3_38
Abstract
Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology that takes advantage of other visual trackers, offline and online. A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The first allows to transfer and compress tracking knowledge of other trackers. The second enables the learning of evaluation measures which are then exploited online. After learning, the student can be ultimately used to build (i) a very fast single-shot tracker, (ii) a tracker with a simple and effective online adaptation mechanism, (iii) a tracker that performs fusion of other trackers. Extensive validation shows that the proposed algorithms compete with real-time state-of-the-art trackers.
arXiv commentAsian Conference on Computer Vision (ACCV) 2020
References in corpus (12)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- High-Speed Tracking with Kernelized Correlation Filters
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- Asynchronous Methods for Deep Reinforcement Learning
- A Novel Performance Evaluation Methodology for Single-Target Trackers
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Massively Parallel Methods for Deep Reinforcement Learning
- Discriminative Correlation Filter with Channel and Spatial Reliability
- Recurrent Neural Network Training with Dark Knowledge Transfer
- Real-Time Correlation Tracking via Joint Model Compression and Transfer
- Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator