Multi-purposing the domain discriminator to supply both domain-invariance and pseudo-label confidence scores in domain adaptation.
Contrastive Adaptation Network for Unsupervised Domain Adaptation
2 Pith papers cite this work, alongside 102 external citations. Polarity classification is still indexing.
2
Pith papers citing it
102
external citations · Pith
abstract
Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. To address this issue, this paper proposes Contrastive Adaptation Network (CAN) optimizing a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy. We design an alternating update strategy for training CAN in an end-to-end manner. Experiments on two real-world benchmarks Office-31 and VisDA-2017 demonstrate that CAN performs favorably against the state-of-the-art methods and produces more discriminative features.
verdicts
UNVERDICTED 2representative citing papers
Unsupervised domain adaptation with GSDE achieves ~80% accuracy in cross-process TIG-laser weld penetration prediction, improving supervised baselines by over 43%.
citing papers explorer
-
Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
Multi-purposing the domain discriminator to supply both domain-invariance and pseudo-label confidence scores in domain adaptation.
-
A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding
Unsupervised domain adaptation with GSDE achieves ~80% accuracy in cross-process TIG-laser weld penetration prediction, improving supervised baselines by over 43%.