Related papers: Continual Improvement of Threshold-Based Novelty D…

Object-based Novelty Detection (ND) aims to identify unknown objects that do not belong to classes seen during training by an object detection model. The task is particularly crucial in real-world applications, as it allows to avoid…

In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural classifiers trained on a closed set of data typically…

Unsupervised novelty detection (UND), aimed at identifying novel samples, is essential in fields like medical diagnosis, cybersecurity, and industrial quality control. Most existing UND methods assume that the training data and testing…

Common variable star classifiers are built only with the goal of producing the correct class labels, leaving much of the multi-task capability of deep neural networks unexplored. We present a periodic light curve classifier that combines a…

Novelty detection in news events has long been a difficult problem. A number of models performed well on specific data streams but certain issues are far from being solved, particularly in large data streams from the WWW where…

We tackle the problem of novel class discovery and localization (NCDL). In this setting, we assume a source dataset with supervision for only some object classes. Instances of other classes need to be discovered, classified, and localized…

Threshold selection is a fundamental problem in any threshold-based extreme value analysis. While models are asymptotically motivated, selecting an appropriate threshold for finite samples is difficult and highly subjective through standard…

Deep learning methods have typically been trained on large datasets in which many training examples are available. However, many real-world product datasets have only a small number of images available for each product. We explore the use…

Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in the unlabeled set.…

Batch Normalization (BN) is an important preprocessing step to many deep learning applications. Since it is a data-dependent process, for some homogeneous datasets it is a redundant or even a performance-degrading process. In this paper, we…

Humans possess an innate ability to identify and differentiate instances that they are not familiar with, by leveraging and adapting the knowledge that they have acquired so far. Importantly, they achieve this without deteriorating the…

We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…

Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…

Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially…

Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in…

We suggest a robust nearest-neighbor approach to classifying high-dimensional data. The method enhances sensitivity by employing a threshold and truncates to a sequence of zeros and ones in order to reduce the deleterious impact of…

In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance.…

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…