BriefGPT.xyz
Aug, 2023
揭示潜在模式:研究数据集相似性、性能和泛化
Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization
HTML
PDF
Akshit Achara, Ram Krishna Pandey
TL;DR
通过添加一小部分未见图片到训练集中,我们的方法可以降低训练与注释成本,提高监督式深度学习模型的泛化性能,并在动态环境中对未见数据的模型性能提供估计。
Abstract
supervised deep learning
models require significant amount of
labelled data
to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore
→