TY  - JOUR
AU  - Huamin Ren
AU  - Nattiya Kanhabua
AU  - Andreas Mogelmose
AU  - Weifeng Liu
AU  - Kaustubh Kulkarni
AU  - Sergio Escalera
AU  - Xavier Baro
AU  - Thomas B. Moeslund
PY  - 2018//
TI  - Back-dropout Transfer Learning for Action Recognition
T2  - IETCV
JO  - IET Computer Vision
SP  - 484
EP  - 491
VL  - 12
IS  - 4
KW  - Learning (artificial intelligence)
KW  - Pattern Recognition
N2  - 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.
UR  - https://ieeexplore.ieee.org/document/8365666
UR  - http://dx.doi.org/10.1049/iet-cvi.2016.0309
N1  - HUPBA; no proj
ID  - Huamin Ren2018
ER  -