Related papers: A Generalization Theory for Zero-Shot Prediction

Machine learning has been considered a promising approach for indoor localization. Nevertheless, the sample efficiency, scalability, and generalization ability remain open issues of implementing learning-based algorithms in practical…

Generalised zero-shot learning (GZSL) is a classification problem where the learning stage relies on a set of seen visual classes and the inference stage aims to identify both the seen visual classes and a new set of unseen visual classes.…

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular,…

Supervised machine learning has several drawbacks that make it difficult to use in many situations. Drawbacks include: heavy reliance on massive training data, limited generalizability and poor expressiveness of high-level semantics.…

Approximate learning machines have become popular in the era of small devices, including quantised, factorised, hashed, or otherwise compressed predictors, and the quest to explain and guarantee good generalisation abilities for such…

Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generative models to combat…

Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the existing methods do not achieve effective knowledge transfer…

The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. It is also a cornerstone of a future "General AI". Any artificially intelligent agent deployed in a…

Learning motion policies from expert demonstrations is an essential paradigm in modern robotics. While end-to-end models aim for broad generalization, they require large datasets and computationally heavy inference. Conversely, learning…

A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models rely solely on statistical learning of how observations change…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic…

Action recognition in surveillance video makes our life safer by detecting the criminal events or predicting violent emergencies. However, efficient action recognition is not free of difficulty. First, there are so many action classes in…

Attribute-based Zero-Shot Learning (ZSL) has revolutionized the ability of models to recognize new classes not seen during training. However, with the advancement of large-scale models, the expectations have risen. Beyond merely achieving…

This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new…

In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of…

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between…

Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of GZSL, semantic information is non-visual data such as a text…

A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of forgetting; yet, despite decades of…

Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to…