Boosting Self-Supervised Learning via Knowledge Transfer
Links to Fileshttps://ieeexplore.ieee.org/document/8579073
MetadataShow full item record
Type of Work9 pages
conference papers and proceedings preprints
Citation of Original PublicationMehdi Noroozi, et.al, Boosting Self-Supervised Learning via Knowledge Transfer, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, DOI: 10.1109/CVPR.2018.00975
RightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
© 2018 IEEE
Subjectslearning (artificial intelligence)
effective transfer strategy
deeper neural network models
novel self-supervised task
In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most effective transfer strategy is fine-tuning, which restricts one to use the same model or parts thereof for both pretext and target tasks. In this paper, we present a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains. In particular, our framework decouples the structure of the self-supervised model from the final task-specific fine-tuned model. This allows us to: 1) quantitatively assess previously incompatible models including handcrafted features; 2) show that deeper neural network models can learn better representations from the same pretext task; 3) transfer knowledge learned with a deep model to a shallower one and thus boost its learning. We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin. Our learned features shrink the mAP gap between models trained via self-supervised learning and supervised learning from 5.9% to 2.6% in object detection on PASCAL VOC 2007.