Transfer Kernel Sparse Coding Based on Dynamic Distribution Alignment for Image Representation

Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new representation of both domains. Most existing works have achieved remarkable results in solving linear domain shift problems, but have poor perfor...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE) s. 230 - 234
Hlavní autoři: Huang, Wei, Gan, Min, Chen, Guangyong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 12.01.2024
Témata:
distribution alignment
domain adaptation
Encoding
Feature extraction
Image coding
Image representation
Sparse approximation
sparse coding
Transfer learning
Visualization
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Sparse coding based domain adaptation methods aim to learn a robust transfer classifier by utilizing the knowledge from source domain and the learned new representation of both domains. Most existing works have achieved remarkable results in solving linear domain shift problems, but have poor performance in nonlinear domain shift problems. In this paper, we propose a Transfer kernel sparse coding based on dynamic distribution alignment (TKSC-DDA) approach for cross-domain visual recognition, which incorporates dynamic distributed alignment into kernel sparse coding to learn discriminative and robust sparse representations. Extensive experiment on visual transfer learning tasks demonstrate that our proposed method can significantly out-perform serval state-of-the-art approaches.
DOI:10.1109/ICCECE61317.2024.10504150