RL-OSHeDA, a two-stage representation learning method with pseudo-labeling, outperforms existing domain adaptation baselines on 56 open-set heterogeneous domain adaptation tasks.
Efficient Learning of Domain-invariant Image Representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present an algorithm that learns representations which explicitly compensate for domain mismatch and which can be efficiently realized as linear classifiers. Specifically, we form a linear transformation that maps features from the target (test) domain to the source (training) domain as part of training the classifier. We optimize both the transformation and classifier parameters jointly, and introduce an efficient cost function based on misclassification loss. Our method combines several features previously unavailable in a single algorithm: multi-class adaptation through representation learning, ability to map across heterogeneous feature spaces, and scalability to large datasets. We present experiments on several image datasets that demonstrate improved accuracy and computational advantages compared to previous approaches.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm
RL-OSHeDA, a two-stage representation learning method with pseudo-labeling, outperforms existing domain adaptation baselines on 56 open-set heterogeneous domain adaptation tasks.