Related papers: Deep Transfer Learning for Multiple Class Novelty …

Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the…

Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be…

One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based…

Training a Deep Neural Network (DNN) from scratch requires a large amount of labeled data. For a classification task where only small amount of training data is available, a common solution is to perform fine-tuning on a DNN which is…

We tackle the problem of novel class discovery, which aims to learn novel classes without supervision based on labeled data from known classes. A key challenge lies in transferring the knowledge in the known-class data to the learning of…

When evaluated in dynamic, open-world situations, neural networks struggle to detect unseen classes. This issue complicates the deployment of continual learners in realistic environments where agents are not explicitly informed when novel…

Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while…

Although CNNs have gained the ability to transfer learned knowledge from source task to target task by virtue of large annotated datasets but consume huge processing time to fine-tune without GPU. In this paper, we propose a new…

Statistical analysis of network data has attracted considerable attention in recent years, due to the rapid advancement of well-trained network models and the accessibility of large public network datasets. In this article, we propose a…

Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter…

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…

Novelty detection is the process of determining whether a query example differs from the learned training distribution. Previous methods attempt to learn the representation of the normal samples via generative adversarial networks (GANs).…

A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved impressive performance on various datasets, they remain…

We utilize neural network embeddings to detect data drift by formulating the drift detection within an appropriate sequential decision framework. This enables control of the false alarm rate although the statistical tests are repeatedly…

Classification is an essential and fundamental task in machine learning, playing a cardinal role in the field of natural language processing (NLP) and computer vision (CV). In a supervised learning setting, labels are always needed for the…

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our…

As a data-driven method, the performance of deep convolutional neural networks (CNN) relies heavily on training data. The prediction results of traditional networks give a bias toward larger classes, which tend to be the background in the…

Recently, CNN object detectors have achieved high accuracy on remote sensing images but require huge labor and time costs on annotation. In this paper, we propose a new uncertainty-based active learning which can select images with more…