DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

TitleDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Publication TypeConference Paper
Year of Publication2014
AuthorsDonahue, J., Jia Y., Vinyals O., Hoffman J., Zhang N., Tzeng E., & Darrell T.
Other Numbers3631
Abstract

We evaluate whether features extracted fromthe activation of a deep convolutional networktrained in a fully supervised fashion on a large,fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generictasks may differ significantly from the originallytrained tasks and there may be insufficient labeled or unlabeled data to conventionally train oradapt a deep architecture to the new tasks. We investigate and visualize the semantic clustering ofdeep convolutional features with respect to a variety of such tasks, including scene recognition,domain adaptation, and fine-grained recognitionchallenges. We compare the efficacy of relyingon various network levels to define a fixed feature, and report novel results that significantlyoutperform the state-of-the-art on several important vision challenges. We are releasing DeCAF,an open-source implementation of these deepconvolutional activation features, along with allassociated network parameters to enable visionresearchers to be able to conduct experimentation with deep representations across a range ofvisual concept learning paradigms.

Bibliographic Notes

Proceedings of the 31st International Conference in Machine Learning (ICML), Beijing, China

Abbreviated Authors

J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, and T. Darrell

ICSI Research Group

Vision

ICSI Publication Type

Article in conference proceedings