Partial Adversarial Domain Adaptation
Domain adversarial learning aligns the feature distributions across the source and target domains in a two-player minimax game. Existing domain adversarial networks generally assume identical label space across different domains. In the presence of big data, there is strong motivation of transferring deep models from existing big domains to unknown small domains. This paper introduces partial domain adaptation as a new domain adaptation scenario, which relaxes the fully shared label space assumption to that the source label space subsumes the target label space. Previous methods typically match the whole source domain to the target domain, which are vulnerable to negative transfer for the partial domain adaptation problem due to the large mismatch between label spaces. We present Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space. Experiments show that PADA exceeds state-of-the-art results for partial domain adaptation tasks on several datasets.
Code (2)
Tasks
Domain AdaptationPartial Domain AdaptationSimilar Papers 제목 키워드 기반
Importance Weighted Adversarial Nets for Partial Domain Adaptation
This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the sourc…
Domain AdaptationPartial Domain AdaptationTransfer LearningUnsupervised Domain Adaptation+1From Big to Small: Adaptive Learning to Partial-Set Domains
Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared acro…
Domain AdaptationPartial Domain AdaptationAdversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challenge
Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Par…
Domain Adaptationdomain classificationPartial Domain AdaptationPartial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network
Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsumes the target one. The key challenge of …
Domain AdaptationPartial Domain AdaptationDomain Adaptation with Incomplete Target Domains
Domain adaptation, as a task of reducing the annotation cost in a target domain by exploiting the existing labeled data in an auxiliary source domain, has received a lot of attention in the research community. However, t…
Domain AdaptationImputation