Related papers: Class Anchor Clustering: a Loss for Distance-based…

In many real-world classification or recognition tasks, it is often difficult to collect training examples that exhaust all possible classes due to, for example, incomplete knowledge during training or ever changing regimes. Therefore,…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the…

In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes. We exploit the peculiarities of NCD to build a new framework, named…

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.…

The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based…

Traditional machine learning follows a close-set assumption that the training and test set share the same label space. While in many practical scenarios, it is inevitable that some test samples belong to unknown classes (open-set). To fix…

Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We reveal a key insight: OOD samples predicted as the same…

Clustering is a popular machine learning technique for data mining that can process and analyze datasets to automatically reveal sample distribution patterns. Since the ubiquitous categorical data naturally lack a well-defined metric space…

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, the cascaded classifier at a…

Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods is limited by their closed-world assumptions, which assume…

Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes. In this work, we first…

Categorical attributes with qualitative values are ubiquitous in cluster analysis of real datasets. Unlike the Euclidean distance of numerical attributes, the categorical attributes lack well-defined relationships of their possible values…

Open-Set Classification (OSC) intends to adapt closed-set classification models to real-world scenarios, where the classifier must correctly label samples of known classes while rejecting previously unseen unknown samples. Only recently,…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning,…

Models trained for classification often assume that all testing classes are known while training. As a result, when presented with an unknown class during testing, such closed-set assumption forces the model to classify it as one of the…

Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to…

It is essential for safety-critical applications of deep neural networks to determine when new inputs are significantly different from the training distribution. In this paper, we explore this out-of-distribution (OOD) detection problem for…

The development of deep convolutional neural network architecture is critical to the improvement of image classification task performance. A lot of studies of image classification based on deep convolutional neural network focus on the…