pith. sign in

arxiv: 2410.23129 · v2 · pith:5DULB7I3new · submitted 2024-10-30 · 💻 cs.LG · cs.CV· stat.ML

Why Fine-grained Labels in Pretraining Benefit Generalization?

classification 💻 cs.LG cs.CVstat.ML
keywords pretrainingdatafine-grainednetworkcoarse-labeledcommondownstreamfeatures
0
0 comments X
read the original abstract

Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data. While there is ample empirical evidence supporting this, the theoretical justification remains an open problem. This paper addresses this gap by introducing a "hierarchical multi-view" structure to confine the input data distribution. Under this framework, we prove that: 1) coarse-grained pretraining only allows a neural network to learn the common features well, while 2) fine-grained pretraining helps the network learn the rare features in addition to the common ones, leading to improved accuracy on hard downstream test samples.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.