Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
- Title
- Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
- Authors
- Jung, Ilchae; Kim, Minji; Park, Eunhyeok; Han, Bohyung
- Date Issued
- 2022-07-27
- Publisher
- International Joint Conferences on Artificial Intelligence
- Abstract
- This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network. The former learns coarse primary information with low cost while the latter conveys residual information for high fidelity to original representations. The proposed parallel architecture is effective to maintain complementary information since fixed-point arithmetic can be utilized in the quantized network and the lightweight model provides precise representations given by a compact channel-pruned network. We incorporate the hybrid representation technique into an online visual tracking task, where deep neural networks need to handle temporal variations of target appearances in real-time. Compared to the state-of-the-art real-time trackers based on conventional deep neural networks, our tracking algorithm demonstrates competitive accuracy on the standard benchmarks with a small fraction of computational cost and memory footprint.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/116838
- Article Type
- Conference
- Citation
- 31st International Joint Conference on Artificial Intelligence, IJCAI 2022, page. 1002 - 1008, 2022-07-27
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.