Adversarial Hard Attention Adaptation
Open Access
- 18 April 2020
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 11 (4), 224
- https://doi.org/10.3390/info11040224
Abstract
Domain adaptation is critical to transfer the invaluable source domain knowledge to the target domain. In this paper, for a particular visual attention model, saying hard attention, we consider to adapt the learned hard attention to the unlabeled target domain. To tackle this kind of hard attention adaptation, a novel adversarial reward strategy is proposed to train the policy of the target domain agent. In this adversarial training framework, the target domain agent competes with the discriminator which takes the attention features generated from the both domain agents as input and tries its best to distinguish them, and thus the target domain policy is learned to align the local attention feature to its source domain counterpart. We evaluated our model on the benchmarks of the cross-domain tasks, such as the centered digits datasets and the enlarged non-centered digits datasets. The experimental results show that our model outperforms the ADDA and other existing methods.Keywords
Funding Information
- National Natural Science Foundation of China-Yunnan Joint Fund (61601230)
This publication has 19 references indexed in Scilit:
- Bayesian Unsupervised Batch and Online Speaker Adaptation of Activation Function Parameters in Deep Models for Automatic Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question AnsweringPublished by Springer Science and Business Media LLC ,2016
- Visual7W: Grounded Question Answering in ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Image Captioning with Semantic AttentionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Simultaneous Deep Transfer Across Domains and TasksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Supervised Sequence Labelling with Recurrent Neural NetworksPublished by Springer Science and Business Media LLC ,2012
- Integrating structured biological data by Kernel Maximum Mean DiscrepancyBioinformatics, 2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997