Transcription of Unsupervised Feature Learning via Non-Parametric Instance ...
{{id}} {{{paragraph}}}
Example: biology
Unsupervised Feature Learning via Non-Parametric Instance ...
Unsupervised Feature Learning via Non-Parametric Instance DiscriminationZhirong Wu? Yuanjun Xiong Stella X. Yu?Dahua Lin ?UC Berkeley / ICSI Chinese University of Hong Kong Amazon RekognitionAbstractNeural net classifiers trained on data with annotatedclass labels can also capture apparent visual similarityamong categories without being directed to do so. We studywhether this observation can be extended beyond the con-ventional domain of supervised Learning : Can we learn agood Feature representation that captures apparent similar-ity among instances, instead of classes, by merely askingthe Feature to be discriminative of individual instances?
Under the conven-tional parametric softmax formulation, for image xwith feature v = f (x), the probability of it being recognized as i-th example is P(ijv) = exp wT i v P n j=1 exp w T j v: (1) where w j is a weight vector for class j, and wT j v measures how well v matches the j-th class i.e., instance. Non-Parametric Classifier. The problem ...
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: