Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Zhang, Jing; Li, Wanqing; Ogunbona, Philip; Xu, Dong

doi:10.1145/3291124

Cited by 99 publications

(85 citation statements)

References 220 publications

(365 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we present different application examples using various visual deep DA methods. Because the information of commonly used datasets for evaluating the performance is provided in [137] in detail, we do not introduce it in this paper.…”

Section: Representation-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Deep visual domain adaptation: A survey

2018

View full text Add to dashboard Cite

Deep domain adaptation has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaptation methods leverage deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning. There have been comprehensive surveys for shallow domain adaptation, but few timely reviews the emerging deep learning based methods. In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions. First, we present a taxonomy of different deep domain adaptation scenarios according to the properties of data that define how two domains are diverged. Second, we summarize deep domain adaptation approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories. Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection. Fourth, some potential deficiencies of current methods and several future directions are highlighted.

show abstract

Section: Representation-based Approachesmentioning

confidence: 99%

“…[20] discussed 38 methods for heterogeneous TL that operate under various settings, requirements, and domains. Zhang et al [137] were the first to summarize several transferring criteria in detail from the concept level. These five surveys mentioned above only cover the methodologies on shallow TL or DA.…”

Section: Introductionmentioning

confidence: 99%

Deep visual domain adaptation: A survey

2018

View full text Add to dashboard Cite

show abstract

“…We first give some notations and definitions which match those from the survey paper written by Pan et al [1], and these notations are also widely adopted in many other survey papers such as [2,3].…”

Section: Overviewmentioning

confidence: 99%

Transfer Learning and Deep Domain Adaptation

Xu¹,

He²,

Shu³

2020

Advances and Applications in Deep Learning

View full text Add to dashboard Cite

Transfer learning is an emerging technique in machine learning, by which we can solve a new task with the knowledge obtained from an old task in order to address the lack of labeled data. In particular deep domain adaptation (a branch of transfer learning) gets the most attention in recently published articles. The intuition behind this is that deep neural networks usually have a large capacity to learn representation from one dataset and part of the information can be further used for a new task. In this research, we firstly present the complete scenarios of transfer learning according to the domains and tasks. Secondly, we conduct a comprehensive survey related to deep domain adaptation and categorize the recent advances into three types based on implementing approaches: fine-tuning networks, adversarial domain adaptation, and sample-reconstruction approaches. Thirdly, we discuss the details of these methods and introduce some typical real-world applications. Finally, we conclude our work and explore some potential issues to be further addressed.

show abstract

“…To address the above-mentioned challenging problem, over the past few years, with the development of transfer learning [2], many methods have been developed. For example, in [3], Chu et al propose a simple yet effective transfer learning method called selective transfer machine (STM), STM can simultaneously learn a classifier and re-weight the training samples that the most relevant to the testing subject.…”

Section: Introductionmentioning

confidence: 99%

Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition

Chen

Song

Zhang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

In this letter, we propose a novel robust transferable subspace learning (RTSL) method for cross-corpus facial expression recognition. In this method, on one hand, we present a novel distance metric algorithm, which jointly considers the local and global distance distribution measure, to reduce the cross-corpus mismatch. On the other hand, we design a label guidance strategy to improve the discriminate ability of subspace. Thus, the RTSL is much more robust to the cross-corpus recognition problem than traditional transfer learning methods. We conduct extensive experiments on several facial expression corpora to evaluate the recognition performance of RTSL. The results demonstrate the superiority of the proposed method over some state-of-the-art methods.

show abstract

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Cited by 99 publications

References 220 publications

Deep visual domain adaptation: A survey

Deep visual domain adaptation: A survey

Transfer Learning and Deep Domain Adaptation

Robust Transferable Subspace Learning for Cross-Corpus Facial Expression Recognition

Contact Info

Product

Resources

About