Journal
IET COMPUTER VISION
Volume 12, Issue 4, Pages 484-491Publisher
WILEY
DOI: 10.1049/iet-cvi.2016.0309
Keywords
learning (artificial intelligence); pattern classification; negative back-dropout transfer learning; action recognition; dataset annotation; vision tasks; classification performance; category bias; NB-TL; UCF 101 dataset
Funding
- MINECO/FEDER, UE [TIN2016-74946-P, TIN2015-66951-C2-2-R]
- CERCA Programme/Generalitat de Catalunya
- European Union's Horizon research and innovation programme under the Marie Sklodowska-Curie grant [752321, 6655919]
- Marie Curie Actions (MSCA) [752321] Funding Source: Marie Curie Actions (MSCA)
Ask authors/readers for more resources
Transfer learning aims at adapting a model learned from source dataset to target dataset. It is a beneficial approach especially when annotating on the target dataset is expensive or infeasible. Transfer learning has demonstrated its powerful learning capabilities in various vision tasks. Despite transfer learning being a promising approach, it is still an open question how to adapt the model learned from the source dataset to the target dataset. One big challenge is to prevent the impact of category bias on classification performance. Dataset bias exists when two images from the same category, but from different datasets, are not classified as the same. To address this problem, a transfer learning algorithm has been proposed, called negative back-dropout transfer learning (NB-TL), which utilizes images that have been misclassified and further performs back-dropout strategy on them to penalize errors. Experimental results demonstrate the effectiveness of the proposed algorithm. In particular, the authors evaluate the performance of the proposed NB-TL algorithm on UCF 101 action recognition dataset, achieving 88.9% recognition rate.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available