Unsupervised Representation Learning by Predicting Image Rotations

作者
Spyros Gidaris,Praveer Singh,Nikos Komodakis
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:1540
标识
DOI:10.48550/arxiv.1803.07728
摘要

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised representation learning and thus significantly close the gap with supervised feature learning. For instance, in PASCAL VOC 2007 detection task our unsupervised pre-trained AlexNet model achieves the state-of-the-art (among unsupervised methods) mAP of 54.4% that is only 2.4 points lower from the supervised case. We get similarly striking results when we transfer our unsupervised learned features on various other tasks, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification. The code and models of our paper will be published on: https://github.com/gidariss/FeatureLearningRotNet .

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
酷酷的鸿完成签到,获得积分10
1秒前
Enfant发布了新的文献求助10
1秒前
1秒前
1秒前
张伟发布了新的文献求助10
1秒前
2秒前
junge发布了新的文献求助10
2秒前
科研通AI6.3的应助被KK采纳,获得40
2秒前
情怀的应助被Aaron采纳,获得10
3秒前
3秒前
成霜完成签到,获得积分10
3秒前
脑洞疼的应助被张张采纳,获得10
3秒前
xx完成签到 ,获得积分10
3秒前
无限的含羞草完成签到,获得积分10
3秒前
qqqq完成签到,获得积分10
3秒前
楚留香完成签到,获得积分10
4秒前
4秒前
筱筱发布了新的文献求助200
5秒前
5秒前
王小冉发布了新的文献求助10
5秒前
5秒前
5秒前
鼻毛好胜完成签到,获得积分10
6秒前
flos完成签到,获得积分10
6秒前
JenifferF完成签到,获得积分10
6秒前
7秒前
千里眼发布了新的文献求助10
8秒前
团子完成签到,获得积分10
8秒前
舒适飞薇发布了新的文献求助10
8秒前
拼搏的亦丝完成签到,获得积分10
8秒前
8秒前
9秒前
苹果梦蕊完成签到 ,获得积分10
9秒前
老大车发布了新的文献求助20
10秒前
不想上班发布了新的文献求助10
10秒前
白龙鱼服完成签到 ,获得积分10
11秒前
周周发布了新的文献求助10
11秒前
11秒前
12秒前
初景的应助被yyc采纳,获得50
12秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8186261
求助须知:如何正确求助?哪些是违规求助? 9574697
关于积分的说明 21837731
捐赠科研通 7783915
什么是DOI,文献DOI怎么找? 3434752
关于科研通互助平台的介绍 2559109
邀请新用户注册赠送积分活动 2481528