A transductive transfer learning approach for image classification

Rezaei, Samaneh; Tahmoresnezhad, Jafar; Solouk, Vahid

doi:10.1007/s13042-020-01200-9

Cited by 13 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the efficiency of our VTL, the results of our experiments are compared with several unsupervised domain adaptation methods including EMFS (2018) [40], EasyTL (2019) [41], STJML (2020) [42], GEF (2019) [43], DWDA (2021) [44], CDMA (2020) [45], ALML (2022) [46], TTLC (2021) [33], SGA-MDAP (2020) [47], NSO (2020) [48], FSUTL (2020) [49], PLC (2021) [50], GSI (2021) [51] and ICDAV (2022) [52]. In the experiments, VTL begins with learning a domain invariant and class discriminative latent feature space according to Equation (18).…”

Section: Resultsmentioning

confidence: 99%

“…Joint geometrical and statistical alignment proposed in [31] tries to pseudo labeling target samples with a source domain classifier and aims to reduce the conditional distribution divergence by iteratively updating the pseudo-labels. The most related works to ours are domain invariant and class discriminative learning (DICD) [32] and transductive transfer learning for image classification (TTLC) [33], which map both the source and target domains into a shared feature space with the least marginal and conditional distribution differences.Both TTLC and DICD utilizing pseudo-labeling of target samples whiteout label correction paradigm so they e Interclass maximization is applied between different classes in both of the source and target domains. Also, VTL maximizes the inter-class distances between different classes across the source and target domains.…”

Section: Methods With Pseudo Labelingmentioning

confidence: 99%

See 1 more Smart Citation

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge across domains when there is no labeled data available in the target domain. In this way, UDA methods attempt to utilize pseudo-labeled target samples to align distribution across the source and target domains. To mitigate the negative impact of inaccurate pseudo-labeling on knowledge transfer, we propose a novel UDA method known as visual transductive learning via iterative label correction (VTL) that benefits from a novel label correction paradigm. Specifically, we learn a domain invariant and class discriminative latent feature representation for samples of both source and target domains. Simultaneously, VTL attempts to locally align the information of samples by learning the geometric structure of samples. In the new shared feature space, the novel label correction paradigm is utilized to effectively maximize the reliability of pseudo labels by correcting inaccurate pseudo-labeled target samples, which significantly improves VTL classification performance. The experimental results on several object recognition tasks verified our proposed VTL superiority in comparison with other state-of-the-arts.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methods With Pseudo Labelingmentioning

confidence: 99%

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Joint marginal and conditional distribution adaptation is a useful method in transfer learning, which measures the distribution shift between domains by a metric such as maximum mean discrepancy (MMD) [ 42 ]. In many joint distribution adaptation based approaches, the marginal and conditional distributions are often treated equally, which may not be optimal [ 9 , 34 , 43 ]. In the other words, if two domains are very dissimilar, it means that the marginal distributions have more discrepancy and need more notice to align; while if two domains are similar (i.e., the marginal distributions are close), it means that the conditional distributions needs more attention and should be given more weight.…”

Section: Introductionmentioning

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