PT Journal
AU Huamin Ren
   Nattiya Kanhabua
   Andreas Mogelmose
   Weifeng Liu
   Kaustubh Kulkarni
   Sergio Escalera
   Xavier Baro
   Thomas B. Moeslund
TI Back-dropout Transfer Learning for Action Recognition
SO IET Computer Vision
JI IETCV
PY 2018
BP 484
EP 491
VL 12
IS 4
DI 10.1049/iet-cvi.2016.0309
DE Learning (artificial intelligence); Pattern Recognition
AB 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.
ER