Context-Aware Deep Feature Compression for High-Speed Visual Tracking

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 479 - 488
• Main Authors: Choi, Jongwon, Chang, Hyung Jin, Fischer, Tobias, Yun, Sangdoo, Lee, Kyuewang, Jeong, Jiyeoup, Demiris, Yiannis, Choi, Jin Young
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Convolutional codes; Correlation; Noise reduction; Real-time systems; Target tracking; Training
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2018.00057

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert autoencoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.