相关论文: Open-World Class Discovery with Kernel Networks

We show how deep learning methods can be applied in the context of crowdsourcing and unsupervised ensemble learning. First, we prove that the popular model of Dawid and Skene, which assumes that all classifiers are conditionally…

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while…

Although deep learning has made significant progress on fixed large-scale datasets, it typically encounters challenges regarding improperly detecting unknown/unseen classes in the open-world scenario, over-parametrized, and overfitting…

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive…

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…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

This paper introduces a generic method which enables to use conventional deep neural networks as end-to-end one-class classifiers. The method is based on splitting given data from one class into two subsets. In one-class classification,…

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

In congested electromagnetic environments, cognitive radios require knowledge about other emitters in order to optimize their dynamic spectrum access strategy. Deep learning classification algorithms have been used to recognize the wireless…

Open-World Continual Learning (OWCL) is a challenging paradigm where models must incrementally learn new knowledge without forgetting while operating under an open-world assumption. This requires handling incomplete training data and…

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has…

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction…

Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existing methods basing on auto-encoder (AE) and prototype learning…

While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training…

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is…

Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…

This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks…

Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…

In open set learning, a model must be able to generalize to novel classes when it encounters a sample that does not belong to any of the classes it has seen before. Open set learning poses a realistic learning scenario that is receiving…