Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning

no code implementations • 10 Mar 2024 • Zijun Long, Lipeng Zhuang, George Killick, Richard McCreadie, Gerardo Aragon Camarasa, Paul Henderson

In this paper, we show that human-labelling errors not only differ significantly from synthetic label errors, but also pose unique challenges in SCL, different to those in traditional supervised learning methods.

Contrastive Learning Representation Learning

CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion

no code implementations • 22 Feb 2024 • Zijun Long, George Killick, Lipeng Zhuang, Gerardo Aragon-Camarasa, Zaiqiao Meng, Richard McCreadie

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).

Contrastive Learning Few-Shot Learning +2

Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning

no code implementations • 25 Nov 2023 • Zijun Long, George Killick, Lipeng Zhuang, Richard McCreadie, Gerardo Aragon Camarasa, Paul Henderson

However, while the detrimental effects of noisy labels in supervised learning are well-researched, their influence on SCL remains largely unexplored.

Contrastive Learning Image Classification +1