Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning
CoRR(2023)
摘要
Image classification datasets exhibit a non-negligible fraction of mislabeled
examples, often due to human error when one class superficially resembles
another. This issue poses challenges in supervised contrastive learning (SCL),
where the goal is to cluster together data points of the same class in the
embedding space while distancing those of disparate classes. While such methods
outperform those based on cross-entropy, they are not immune to labeling
errors. However, while the detrimental effects of noisy labels in supervised
learning are well-researched, their influence on SCL remains largely
unexplored. Hence, we analyse the effect of label errors and examine how they
disrupt the SCL algorithm's ability to distinguish between positive and
negative sample pairs. Our analysis reveals that human labeling errors manifest
as easy positive samples in around 99% of cases. We, therefore, propose D-SCL,
a novel Debiased Supervised Contrastive Learning objective designed to mitigate
the bias introduced by labeling errors. We demonstrate that D-SCL consistently
outperforms state-of-the-art techniques for representation learning across
diverse vision benchmarks, offering improved robustness to label 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