Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samples

arXiv:2311.06056v2 Announce Type: replace
Abstract: In the field of intelligent multimedia analysis, ultra-fine-grained visual categorization (Ultra-FGVC) plays a vital role in distinguishing intricate subcategories within broader categories. However, this task is inherently challenging due to the complex granularity of category subdivisions and the limited availability of data for each category. To address these challenges, this work proposes CSDNet, a pioneering framework that effectively explores contrastive learning and self-distillation to learn discriminative representations specifically designed for Ultra-FGVC tasks. CSDNet comprises three …

abstract analysis arxiv availability cs.cv cs.mm data distillation fine-grained intelligent multimedia role samples targeting type visual vital