OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

Chengkun Wang, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu

Keywords: Representation learning, omni-supervised learning.

Abstract: The pretrain-finetune paradigm in modern computer vision facilitates the success of self-supervised learning, which tends to achieve better transferability than supervised learning. However, with the availability of massive labeled data, a natural question emerges: how to train a better model with both self and full supervision signals? In this paper, we propose omni-supervised representation learning with hierarchical supervisions (OPERA) as a solution. We provide a unified perspective of supervisions from labeled and unlabeled data and propose a unified framework of fully supervised and self-supervised learning. We extract a set of hierarchical proxy representations for each image and impose self and full supervisions on the corresponding proxy representations. Extensive experiments on both convolutional neural networks and vision transformers demonstrate the superiority of OPERA in image classification, segmentation, and object detection.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: We propose an omni-supervised representation learning with hierarchical supervisions method for better transferability.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2210.05557/code)