One-Class Convolutional Neural Network

@article{Oza2019OneClassCN,
  title={One-Class Convolutional Neural Network},
  author={Poojan Oza and Vishal M. Patel},
  journal={IEEE Signal Processing Letters},
  year={2019},
  volume={26},
  pages={277-281}
}
We present a novel convolutional neural network (CNN) based approach for one-class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one-class classification. The proposed one-class CNN is… Expand
Learning Deep Features for One-Class Classification
TLDR
A novel deep-learning-based approach for one-class transfer learning in which labeled data from an unrelated task is used for feature learning in one- class classification and achieves significant improvements over the state-of-the-art. Expand
Utilizing Patch-Level Category Activation Patterns for Multiple Class Novelty Detection
TLDR
A novel method that makes deep convolutional neural networks robust to novel classes by combining global and local branch information to train a novelty detection network, which is used during inference to identify novel classes. Expand
Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier
  • Poojan Oza, Vishal M. Patel
  • Computer Science
  • 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)
  • 2019
TLDR
A convolutional neural network (CNN) based approach for one class classification in which a zero centered Gaussian noise and an autoencoder are used to model the pseudo-negative class and to regularize the network to learn meaningful feature representations for oneclass data, respectively. Expand
Deep Transfer Learning for Multiple Class Novelty Detection
TLDR
It is shown that thresholding the maximal activation of the proposed network can be used to identify novel objects effectively, and that the proposed method achieves significant improvements over the state-of-the-art methods. Expand
Enhanced Convolutional Neural Network for Abnormal Event Detection in Video Streams
TLDR
This paper proposes a novel one-class neural network technique suitable for outliers detection that takes advantage of the deep learning ability in image processing, while meeting the constraint of using only training samples from the target class. Expand
One-Class Classification: A Survey
TLDR
A survey of classical statistical and recent deep learning-based OCC methods for visual recognition discusses the merits and drawbacks of existing OCC approaches and identifies promising avenues for research in this field. Expand
A Joint Representation Learning and Feature Modeling Approach for One-class Recognition
TLDR
This work argues that both of these approaches have their own limitations; and a more effective solution can be obtained by combining the two, based on the combination of a generative framework and a one-class classification method. Expand
Discriminative-Generative Representation Learning for One-Class Anomaly Detection
TLDR
A self-supervised learning framework combining generative methods and discriminative methods so that the generator no longer learns representation by reconstruction error, but the guidance of discriminator, and could benefit from pretext tasks designed for discriminatives methods. Expand
Generative-Discriminative Feature Representations for Open-Set Recognition
TLDR
This work proposes two techniques to force class activations of open-set samples to be low, and uses self-supervision to force the network to learn more informative featues when assigning class scores to improve separation of classes from each other and from open- set samples. Expand
OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations
TLDR
A novel model called OCGAN is presented for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if a query example is from the same class using a de-noising auto-encoder network. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
Learning Deep Features for One-Class Classification
TLDR
A novel deep-learning-based approach for one-class transfer learning in which labeled data from an unrelated task is used for feature learning in one- class classification and achieves significant improvements over the state-of-the-art. Expand
Anomaly Detection using One-Class Neural Networks
TLDR
A comprehensive set of experiments demonstrate that on complex data sets (like CIFAR and PFAM), OC-NN significantly outperforms existing state-of-the-art anomaly detection methods. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Adversarially Learned One-Class Classifier for Novelty Detection
TLDR
The results on MNIST and Caltech-256 image datasets, along with the challenging UCSD Ped2 dataset for video anomaly detection illustrate that the proposed method learns the target class effectively and is superior to the baseline and state-of-the-art methods. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes. Expand
Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes
TLDR
An FCN-based architecture for anomaly detection and localization in crowded scenes videos is proposed, which includes two main components, one for feature representation, and one for cascaded out-layer detection. Expand
High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning
TLDR
A hybrid model where an unsupervised DBN is trained to extract generic underlying features, and a one-class SVM is trained from the features learned by the DBN, which delivers a comparable accuracy with a deep autoencoder and is scalable and computationally efficient. Expand
Incremental Kernel Null Space Discriminant Analysis for Novelty Detection
TLDR
Experiments demonstrate that the proposed Incremental Kernel Null Space based Discriminant Analysis (IKNDA) algorithm yields comparable performance as the batch KNDA yet significantly reduces the computational complexity, and markedly outperform approaches using deep neural network (DNN) classifiers. Expand
The Pascal Visual Object Classes (VOC) Challenge
TLDR
The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse. Expand
...
1
2
3
4
...