相关论文: Informed Democracy: Voting-based Novelty Detection…

Novelty detection is a process for distinguishing the observations that differ in some respect from the observations that the model is trained on. Novelty detection is one of the fundamental requirements of a good classification or…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

State-of-the-art deep neural network recognition systems are designed for a static and closed world. It is usually assumed that the distribution at test time will be the same as the distribution during training. As a result, classifiers are…

We address the problem of novelty detection in multiclass scenarios where some class labels are missing from the training set. Our method is based on the initial assignment of confidence values, which measure the affinity between a new test…

State-of-the-art results in typical classification tasks are mostly achieved by unexplainable machine learning methods, like deep neural networks, for instance. Contrarily, in this paper, we investigate the application of rule learning…

Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image. We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear…

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose…

Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to…

In this paper we present a novel method for a naive agent to detect novel objects it encounters in an interaction. We train a reinforcement learning policy on a stacking task given a known object type, and then observe the results of the…

We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensing tasks, including the detection of local surface changes:…

Human beings not only have the ability to recognize novel unseen classes, but also can incrementally incorporate the new classes to existing knowledge preserved. However, zero-shot learning models assume that all seen classes should be…

In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only). Moreover, new unknown…

Activity recognition is a challenging problem with many practical applications. In addition to the visual features, recent approaches have benefited from the use of context, e.g., inter-relationships among the activities and objects.…

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on…

Novelty detection plays an important role in machine learning and signal processing. This paper studies novelty detection in a new setting where the data object is represented as a bag of instances and associated with multiple class labels,…

Zero-shot learning is a new paradigm to classify objects from classes that are not available at training time. Zero-shot learning (ZSL) methods have attracted considerable attention in recent years because of their ability to classify…

Machine learning-based techniques open up many opportunities and improvements to derive deeper and more practical insights from data that can help businesses make informed decisions. However, the majority of these techniques focus on the…

Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of…

The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly.…

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…