10 surveys about transfer learning and domain adaptation in the domain of computer vision you need to read:
A Survey on Transfer Learning (2010)
The survey categorizes and reviews transfer learning's progress for classification, regression, and clustering, discussing its relationship with domain adaptation, multitask learning, and co-variate shift. → read here
Transfer learning for activity recognition: a survey (2013)
It characterizes approaches by sensor modality, environment differences, data availability, and information type transferred. → read here
Visual Domain Adaptation A survey of recent advances (2015)
This survey reviews visual recognition domain adaptation methods, evaluates their strengths and limitations, and identifies promising research areas. → read here
Transfer learning using computational intelligence: A survey (2015)
It systematizes computational intelligence-based transfer learning techniques into categories like neural networks and Bayes-based methods and discusses their applications. → read here
Transfer Learning for Visual Categorization: A Survey (2015)
It surveys algorithms in object recognition, image classification, and human action recognition, highlighting transfer learning's role in leveraging cross-domain data. → read here
Deep visual domain adaptation: A survey (2015)
It introduces a taxonomy of adaptation scenarios, summarizes approaches by training loss, and reviews applications beyond image classification. → read here
A survey of transfer learning (2016)
Defines transfer learning, reviewing solutions and applications in contexts where training and testing data domains differ. It discusses transfer learning's applicability in big data environments. → read here
A survey of transfer learning for collaborative recommendation with auxiliary data
The survey discusses the role of Intelligent Recommendation Technology in industries like e-commerce, focusing on Collaborative Recommendation with Auxiliary Data. → read here
Extreme learning machine based transfer learning algorithms: A survey (2017)
It provides a comprehensive overview of ELM-based transfer learning, serving as a guide for new researchers and identifying future research avenues. → read here
Domain adaptation for visual applications: A comprehensive survey (2017)
It discusses shallow and deep domain adaptation methods, and their effects on various visual tasks, and relates domain adaptation to other machine learning solutions. → read here
Every day we post helpful lists and bite-sized explanations on our X (Twitter). Please join us there: