Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
arxiv(2024)
摘要
Human-annotated vision datasets inevitably contain a fraction of human
mislabelled examples. While the detrimental effects of such mislabelling on
supervised learning are well-researched, their influence on Supervised
Contrastive Learning (SCL) remains largely unexplored. 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. Specifically, our results indicate
they adversely impact the learning process in the 99
as false positive samples. Existing noise-mitigating methods primarily focus on
synthetic label errors and tackle the unrealistic setting of very high
synthetic noise rates (40-80
datasets due to overfitting. To address this issue, we introduce a novel SCL
objective with robustness to human-labelling errors, SCL-RHE. SCL-RHE is
designed to mitigate the effects of real-world mislabelled examples, typically
characterized by much lower noise rates (<5
consistently outperforms state-of-the-art representation learning and
noise-mitigating methods across various vision benchmarks, by offering improved
resilience against human-labelling errors.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要