# OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions

Source: [OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisions](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:48:10.793Z

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

Published: 2022-10-11T15:51:31.000Z

## 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. Code is available at: https://github.com/wangck20/OPERA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.05557>)

[PDF](<https://arxiv.org/pdf/2210.05557.pdf>)