Faster Domain Adaptation Networks
Top Cited Papers
- 19 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (12), 5770-5783
- https://doi.org/10.1109/tkde.2021.3060473
Abstract
It is widely acknowledged that the success of deep learning is built on large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we address the machine learning problem where it lacks training data and limits computing power. Specifically, we investigate domain adaptation which is able to transfer knowledge from one labeled source domain to an unlabeled target domain, so that we do not need much training data from the target domain. At the same time, we consider the situation that the running environment is confined, e.g., in edge computing the end device has very limited running resources. Technically, we present the Faster Domain Adaptation (FDA) protocol and further report two paradigms of FDA: early stopping and amid skipping. The former accelerates domain adaptation by multiple early exit points. The latter speeds up the adaptation by wisely skip several amid neural network blocks. Extensive experiments on standard benchmarks verify that our method is able to achieve the comparable and even better accuracy but employ much less computing resources. To the best of our knowledge, there are very few works which investigated accelerating knowledge adaptation in the community.Keywords
Funding Information
- National Natural Science Foundation of China (61806039, 62073059, 61832001)
- Sichuan Science and Technology Program (2020YFG0080)
This publication has 29 references indexed in Scilit:
- Two Birds One StonePublished by Association for Computing Machinery (ACM) ,2017
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Adversarial Discriminative Domain AdaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Incomplete Multisource Transfer LearningIEEE Transactions on Neural Networks and Learning Systems, 2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Learning Cross-Domain Landmarks for Heterogeneous Domain AdaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998