Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

About

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.

Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, Trevor Darrell• 2013

Related benchmarks

TaskDatasetResultRank
Fine-grained Image ClassificationCUB200 2011 (test)
Accuracy64.96
536
Image ClassificationCUB-200-2011 (test)--
276
Domain AdaptationOffice-31 unsupervised adaptation standard
Accuracy (A to W)61.6
162
Image ClassificationOffice-10 + Caltech-10
Average Accuracy84
77
object recognitionOffice (standard)
Accuracy (A to W)53.9
55
ClassificationCaltech101 (test)
Accuracy86.91
33
Dynamic Scene RecognitionYUPENN (leave-one-out)
Accuracy96.7
12
Image ClassificationOFFICE DSLR → Webcam (test)
Accuracy91.5
8
Image ClassificationOFFICE Amazon → Webcam (test)
Accuracy52.2
8
Multi-class classificationOffice standard evaluation
Accuracy (A->W)0.807
7
Showing 10 of 19 rows

Other info

Follow for update