Nov. 5, 2023, 6:49 a.m. | Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong, Hansang Cho, Junmo Kim

cs.CV updates on arXiv.org arxiv.org

Recent advances in deep learning have significantly improved the performance
of various computer vision applications. However, discovering novel categories
in an incremental learning scenario remains a challenging problem due to the
lack of prior knowledge about the number and nature of new categories. Existing
methods for novel category discovery are limited by their reliance on labeled
datasets and prior knowledge about the number of novel categories and the
proportion of novel samples in the batch. To address the limitations and …

advances anchor applications arxiv computer computer vision continuous deep learning discovery generalized incremental knowledge nature novel performance prior unsupervised unsupervised learning vision

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote