计算机科学
卷积神经网络
人工智能
深度学习
特征(语言学)
域适应
集合(抽象数据类型)
视觉对象识别的认知神经科学
模式识别(心理学)
适应(眼睛)
多样性(控制论)
领域(数学分析)
机器学习
特征提取
数学分析
物理
哲学
光学
分类器(UML)
程序设计语言
语言学
数学
作者
Jeff Donahue,Yangqing Jia,Oriol Vinyals,Judy Hoffman,Ning Zhang,Eric Tzeng,Trevor Darrell
出处
期刊:Cornell University - arXiv
日期:2013-01-01
被引量:1881
标识
DOI:10.48550/arxiv.1310.1531
摘要
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks may differ significantly from the originally trained tasks and there may be insufficient labeled or unlabeled data to conventionally train or adapt a deep architecture to the new tasks. We investigate and visualize the semantic clustering of deep convolutional features with respect to a variety of such tasks, including scene recognition, domain adaptation, and fine-grained recognition challenges. We compare the efficacy of relying on various network levels to define a fixed feature, and report novel results that significantly outperform the state-of-the-art on several important vision challenges. We are releasing DeCAF, an open-source implementation of these deep convolutional activation features, along with all associated network parameters to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms.
科研通智能强力驱动
Strongly Powered by AbleSci AI