Transcription of Bilinear CNN Models for Fine-grained Visual Recognition
{{id}} {{{paragraph}}}
Example: tourism industry
Bilinear CNN Models for Fine-grained Visual Recognition
Bilinear CNN Models for Fine-grained Visual RecognitionTsung-Yu LinAruni RoyChowdhurySubhransu MajiUniversity of Massachusetts, propose Bilinear Models , a Recognition architecturethat consists of two feature extractors whose outputs aremultiplied using outer product at each location of the im-age and pooled to obtain an image descriptor. This archi-tecture can model local pairwise feature interactions in atranslationally invariant manner which is particularly use-ful for Fine-grained categorization. It also generalizes var-ious orderless texture descriptors such as the Fisher vec-tor, VLAD and O2P. We present experiments with bilinearmodels where the feature extractors are based on convolu-tional neural networks.
the classification function C we use logistic regression or linear SVM. This can be replaced with a multi-layer neural network if non-linearity is desirable. End-to-end training Since the overall architecture is a directed acyclic graph the parameters can be trained by back-propagating the gradients of the classification loss
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: