When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks
arXiv:1511.03853
Abstract
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features; (2) they cannot be used as final layer of CNN architectures for end-to-end training , and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from local patches at multiple scale levels, similarly to [1]. We address simultaneously the second and third by proposing a scalable version of Naive Bayes Non-linear Learning (NBNL, [2]). Results obtained using pre-trained CNNs on standard scene and domain adaptation databases show the strength of our approach, opening a new season for NBNNs.
References in corpus (5)
- Caffe: Convolutional Architecture for Fast Feature Embedding
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning Transferable Features with Deep Adaptation Networks
- Return of the Devil in the Details: Delving Deep into Convolutional Nets
- A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets