TY - JOUR
T1 - Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
AU - Choudhuri, Sandipan
AU - Venkateswara, Hemanth
AU - Sen, Arunabha
N1 - Publisher Copyright:
© The Author(s) 2022.
PY - 2022/11/18
Y1 - 2022/11/18
N2 - In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discriminative and domain-invariant features by coupling the process of achieving compact and distinct class distributions with an adversarial objective. Experimental findings over numerous cross-domain classification tasks demonstrate the potential of the proposed technique to deliver superior and comparable accuracy over existing methods.
AB - In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discriminative and domain-invariant features by coupling the process of achieving compact and distinct class distributions with an adversarial objective. Experimental findings over numerous cross-domain classification tasks demonstrate the potential of the proposed technique to deliver superior and comparable accuracy over existing methods.
KW - adversarial learning
KW - class-distribution alignment
KW - domain adaptation
KW - partial domain adaptation
UR - http://www.scopus.com/inward/record.url?scp=85144288203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85144288203&partnerID=8YFLogxK
U2 - 10.47852/bonviewJCCE2202324
DO - 10.47852/bonviewJCCE2202324
M3 - Article
AN - SCOPUS:85144288203
SN - 2810-9570
VL - 1
SP - 181
EP - 186
JO - Journal of Computational and Cognitive Engineering
JF - Journal of Computational and Cognitive Engineering
IS - 4
ER -