Papers
arxiv:2203.04668

Towards Inadequately Pre-trained Models in Transfer Learning

Published on Mar 9, 2022
Authors:
,
,
,
,
,

Abstract

Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to have better transferability to downstream tasks. However, in this paper, we found that during the same pre-training process, models at middle epochs, which is inadequately pre-trained, can outperform fully trained models when used as feature extractors (FE), while the fine-tuning (FT) performance still grows with the source performance. This reveals that there is not a solid positive correlation between top-1 accuracy on ImageNet and the transferring result on target data. Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations. Our discoveries suggest that, during pre-training, models tend to first learn spectral components corresponding to large singular values and the residual components contribute more when fine-tuning.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2203.04668 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2203.04668 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2203.04668 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.