Multi-source domain adaptation for image classification

Karimpour, Morvarid; Saray, Shiva Noori; Tahmoresnezhad, Jafar; Aghababa, Mohammad Pourmahmood

doi:10.1007/s00138-020-01093-2

Cited by 21 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The scope of transfer learning is very wide, including homogeneous and heterogeneous transfer learning [ 19 ], visual domain adaptation [ 15 , 36 , 40 ] and cross-dataset recognition [ 50 ], which is applicable in various areas such as object recognition [ 8 ], text classification [ 16 ], speech recognition [ 12 ] and face recognition [ 49 ].…”

Section: Related Workmentioning

confidence: 99%

Iterative joint classifier and domain adaptation for visual transfer learning

Saray

Tahmoresnezhad

2021

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

Current available supervised classifiers cannot generalize across various domains due to distribution mismatch among them. Domain adaptation and transfer learning algorithms are proposed to tackle domain shift problem that originates from different data collection conditions. In this paper, we propose a transfer learning framework called iterative joint classifier and domain adaptation for visual transfer learning (ICDAV), which utilizes the balanced maximum mean discrepancy to better transfer knowledge across domains. Also, for learning a robust classifier against domain shift, a set of graph manifold regularizer and modified joint probability maximum mean discrepancy are simultaneously exploited to capture the domain structures and adapt the distribution of projected samples during the model learning process. Variety of experiments on several public datasets indicates that our approach achieves remarkable performance on visual domain adaptation and transfer learning tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Iterative joint classifier and domain adaptation for visual transfer learning

Saray

Tahmoresnezhad

2021

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kernel-based methods, like maximum mean discrepancy [23], try to align feature distributions of the involved domains by using a cost function on a shared feature extractor that should minimize the distance between distributions. This is applied for example in [24,25,26,27,28,29]. Approaches using adversarial methods [30,31] are mostly based on a regressor or a full domain classifier that is additionally attached to the shared feature extractor.…”

Section: Related Workmentioning

confidence: 99%

Improved Multi-Source Domain Adaptation by Preservation of Factors

Schrom¹,

Hasler²,

Adamy³

2020

Preprint

View full text Add to dashboard Cite

Domain Adaptation (DA) is a highly relevant research topic when it comes to image classification with deep neural networks. Combining multiple source domains in a sophisticated way to optimize a classification model can improve the generalization to a target domain. Here, the difference in data distributions of source and target image datasets plays a major role. In this paper, we describe based on a theory of visual factors how real-world scenes appear in images in general and how recent DA datasets are composed of such. We show that different domains can be described by a set of so called domain factors, whose values are consistent within a domain, but can change across domains. Many DA approaches try to remove all domain factors from the feature representation to be domain invariant. In this paper we show that this can lead to negative transfer since task-informative factors can get lost as well. To address this, we propose Factor-Preserving DA (FP-DA), a method to train a deep adversarial unsupervised DA model, which is able to preserve specific task relevant factors in a multi-domain scenario. We demonstrate on CORe50 [1], a dataset with many domains, how such factors can be identified by standard one-to-one transfer experiments between single domains combined with PCA. By applying FP-DA, we show that the highest average and minimum performance can be achieved.

show abstract

“…Similar to SDA, a straightforward approach for multi-source domain adaptation (MDA) to deal with multi-source data is also to merge all sources into one domain [39], which leads to an insufficient variance elimination in MSST [36]. In order to fully exploit multiple subjects' data distribution, some MDA began exploring feature representation approaches and combination of pre-learned classifiers [39][40][41][42][43]. The former approaches try to align the latent space of different domains based on optimizing the discrepancy loss, such as Rényi-divergence [48], L2 distance [49] or align the features through adversarial objectives, such as GAN loss [57], Wasserstein distance [58], [69].…”

Section: Introductionmentioning

confidence: 99%

SFDA: Domain Adaptation With Source Subject Fusion Based on Multi-Source and Single-Target Fall Risk Assessment

Wu,

Shu,

Song

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

In cross-subject fall risk classification based on plantar pressure, a challenge is that data from different subjects have significant individual information. Thus, the models with insufficient generalization ability can't perform well on new subjects, which limits their application in daily life. To solve this problem, domain adaptation methods are applied to reduce the gap between source and target domain. However, these methods focus on the distribution of the source and the target domain, but ignore the potential correlation among multiple source subjects, which deteriorates domain adaptation performance. In this paper, we proposed a novel method named domain adaptation with subject fusion (SFDA) for fall risk assessment, greatly improving the cross-subject assessment ability. Specifically, SFDA synchronously carries out source target adaptation and multiple source subject fusion by domain adversarial module to reduce source-target gap and distribution distance within source subjects of same class. Consequently, target samples can learn more task-specific features from source subjects to improve the generalization ability. Experiment results show that SFDA achieved mean accuracy of 79.17 % and 73.66 % based on two backbones in a cross-subject classification manner, outperforming the state-of-the-art methods on continuous plantar pressure dataset. This study proves the effectiveness of SFDA and provides a novel tool for implementing cross-subject and few-gait fall risk assessment.

show abstract

Multi-source domain adaptation for image classification

Cited by 21 publications

References 23 publications

Iterative joint classifier and domain adaptation for visual transfer learning

Iterative joint classifier and domain adaptation for visual transfer learning

Improved Multi-Source Domain Adaptation by Preservation of Factors

SFDA: Domain Adaptation With Source Subject Fusion Based on Multi-Source and Single-Target Fall Risk Assessment

Contact Info

Product

Resources

About