all AI news
CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Feb. 23, 2024, 5:43 a.m. | Zijun Long, George Killick, Lipeng Zhuang, Gerardo Aragon-Camarasa, Zaiqiao Meng, Richard Mccreadie
cs.LG updates on arXiv.org arxiv.org
Abstract: State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been demonstrated that CE can compromise model generalization and stability. While recent works employing contrastive learning address some of these limitations by enhancing the quality of embeddings and producing better decision boundaries, they often overlook the importance of hard negative mining and rely on resource intensive and slow training using …
abstract art arxiv cross-entropy cs.ai cs.cv cs.lg datasets entropy fine-tuning fusion image loss model generalization pre-training scale stability stage state training type unsupervised
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne