Self-Tuning for Data-Efficient Deep Learning

Ximei Wang · Jinghan Gao · Mingsheng Long · Jianmin Wang

Keywords: [ Deep Learning ]

[ Abstract ]
[ Slides [ Paper ] [ Visit Poster at Spot B5 in Virtual World ]
Tue 20 Jul 9 a.m. PDT — 11 a.m. PDT
Spotlight presentation: Deep Learning Algorithms 1
Tue 20 Jul 6 a.m. PDT — 7 a.m. PDT

Abstract: Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios. To mitigate the requirement for labeled data, semi-supervised learning (SSL) focuses on simultaneously exploring both labeled and unlabeled data, while transfer learning (TL) popularizes a favorable practice of fine-tuning a pre-trained model to the target data. A dilemma is thus encountered: Without a decent pre-trained model to provide an implicit regularization, SSL through self-training from scratch will be easily misled by inaccurate pseudo-labels, especially in large-sized label space; Without exploring the intrinsic structure of unlabeled data, TL through fine-tuning from limited labeled data is at risk of under-transfer caused by model shift. To escape from this dilemma, we present Self-Tuning to enable data-efficient deep learning by unifying the exploration of labeled and unlabeled data and the transfer of a pre-trained model, as well as a Pseudo Group Contrast (PGC) mechanism to mitigate the reliance on pseudo-labels and boost the tolerance to false labels. Self-Tuning outperforms its SSL and TL counterparts on five tasks by sharp margins, e.g. it doubles the accuracy of fine-tuning on Cars with $15\%$ labels.

Chat is not available.