A survey of deep domain adaptation based on label set classification

Fan, Min; Cai, Ziyun; Zhang, Tengfei; Wang, Baoyun

doi:10.1007/s11042-022-12630-8

Cited by 5 publications

(3 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods have been developed in the last decade to overcome the problem of domain shift. Those methods can be categorized according to [15] into instance-based, feature-based, and parameter-based methods. Because parameter-based methods focus on adjusting the model's parameters, which is not in the scope of our work, we refer to [14] for related methods.…”

Section: Related Workmentioning

confidence: 99%

“…(1) Instance-based methods adjust the weights of the instances in a way such that the distributions of both domains are similar [15]. Gong et al [16] automatically selected instances from the source domain ("landmarks") that were distributed similarly to the target domain in order to mitigate the domain shift problem.…”

Section: Related Workmentioning

confidence: 99%

“…(2) Feature-based methods achieve domain adaptation by adjusting the features of two domains [15]. Many approaches try to alleviate the domain discrepancy by projecting both domains in a common embedding space [18][19][20].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Similarity-Based Framework for Unsupervised Domain Adaptation: Peer Reviewing Policy for Pseudo-Labeling

Arweiler,

Ates,

Cerquides

et al. 2023

MAKE

View full text Add to dashboard Cite

The inherent dependency of deep learning models on labeled data is a well-known problem and one of the barriers that slows down the integration of such methods into different fields of applied sciences and engineering, in which experimental and numerical methods can easily generate a colossal amount of unlabeled data. This paper proposes an unsupervised domain adaptation methodology that mimics the peer review process to label new observations in a different domain from the training set. The approach evaluates the validity of a hypothesis using domain knowledge acquired from the training set through a similarity analysis, exploring the projected feature space to examine the class centroid shifts. The methodology is tested on a binary classification problem, where synthetic images of cubes and cylinders in different orientations are generated. The methodology improves the accuracy of the object classifier from 60% to around 90% in the case of a domain shift in physical feature space without human labeling.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%