Generative-Discriminative Variational Model for Visual Recognition
The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN), how to alleviate overfitting during training has been a research topic of interest. In this paper, we present a Generative-Discriminative Variational Model (GDVM) for visual classification, in which we introduce a latent variable inferred from inputs for exhibiting generative abilities towards prediction. In other words, our GDVM casts the supervised learning task as a generative learning process, with data discrimination to be jointly exploited for improved classification. In our experiments, we consider the tasks of multi-class classification, multi-label classification, and zero-shot learning. We show that our GDVM performs favorably against the baselines or recent generative DNN models.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationmodelMulti-class ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONZero-Shot LearningSimilar Papers 제목 키워드 기반
A Generative Parser with a Discriminative Recognition Algorithm
Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative mo…
Constituency ParsingDecoderLanguage ModelingLanguage Modelling+1Discriminative Regularization for Generative Models
We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are…
Open Set Recognition with Conditional Probabilistic Generative Models
Deep neural networks have made breakthroughs in a wide range of visual understanding tasks. A typical challenge that hinders their real-world applications is that unknown samples may be fed into the system during the tes…
Open Set LearningDeep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition
In this study, we apply the information-theoretic Privacy Funnel (PF) model to the domain of face recognition, developing a novel method for privacy-preserving representation learning within an end-to-end training framew…
Face RecognitionPrivacy PreservingRepresentation LearningControversial stimuli: pitting neural networks against each other as models of human recognition
Distinct scientific theories can make similar predictions. To adjudicate between theories, we must design experiments for which the theories make distinct predictions. Here we consider the problem of comparing deep neura…
Adversarial Attack