Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective

2017/05/11 by Jing Zhang, Wanqing Li, Zhang, Jing +5 · 1 citation
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.1705.04396

openalex publication_date 2017/05/11 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition, but also the problems (e.g. eight of the seventeen problems) that have been scarcely studied. This survey not only presents an up-to-date technical review for researchers, but also a systematic approach and a reference for a machine learning practitioner to categorise a real problem and to look up for a possible solution accordingly.

Citations

• Deep Domain Confusion: Maximizing for Domain Invariance
• Visual Domain Adaptation: A survey of recent advances
• A unifying view on dataset shift in classification
• Domain Generalization via Invariant Feature Representation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Learning Bound for Parameter Transfer Learning
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Partial Transfer Learning with Selective Adversarial Networks

Cited by

• You Are What You Write: Author re-identification privacy attacks in the era of pre-trained language models

Related

• Visual Transfer Learning: Informal Introduction and Literature Overview
• Transfer Learning Applied to Computer Vision Problems: Survey on Current Progress, Limitations, and Opportunities
• Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types
• Learning to see across Domains and Modalities
• When & How to Transfer with Transfer Learning