ImbaGCD: Imbalanced Generalized Category Discovery

no code implementations • 4 Dec 2023 • Ziyun Li, Ben Dai, Furkan Simsek, Christoph Meinel, Haojin Yang

Therefore, we present a challenging and practical problem, Imbalanced Generalized Category Discovery (ImbaGCD), where the distribution of unlabeled data is imbalanced, with known classes being more frequent than unknown ones.

DocLangID: Improving Few-Shot Training to Identify the Language of Historical Documents

1 code implementation • 3 May 2023 • Furkan Simsek, Brian Pfitzmann, Hendrik Raetz, Jona Otholt, Haojin Yang, Christoph Meinel

In this work, we propose DocLangID, a transfer learning approach to identify the language of unlabeled historical documents.

Few-Shot Learning Language Identification +1