Hybrid Replay, a federated class-incremental method combining latent exemplar replay with centroid-based synthetic data generation, reports higher accuracy than prior baselines on multiple image benchmarks.
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, the complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
Hybrid Replay, a federated class-incremental method combining latent exemplar replay with centroid-based synthetic data generation, reports higher accuracy than prior baselines on multiple image benchmarks.