Kavli Affiliate: Zheng Zhu
| First 5 Authors: Chengkun Wang, Wenzhao Zheng, Zheng Zhu, Jie Zhou, Jiwen Lu
| Summary:
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. Code is available at: https://github.com/wangck20/OPERA.
| Search Query: ArXiv Query: search_query=au:”Zheng Zhu”&id_list=&start=0&max_results=10