One-Shot Domain Incremental Learning

arXiv:2403.16707v1 Announce Type: new
Abstract: Domain incremental learning (DIL) has been discussed in previous studies on deep neural network models for classification. In DIL, we assume that samples on new domains are observed over time. The models must classify inputs on all domains. In practice, however, we may encounter a situation where we need to perform DIL under the constraint that the samples on the new domain are observed only infrequently. Therefore, in this study, we consider the extreme case …

abstract arxiv classification cs.ai cs.cv cs.lg deep neural network domain domains however incremental inputs network neural network practice samples studies type