Related papers: Semantic Novelty Detection via Relational Reasonin…

Comprehensive scene understanding is a critical enabler of robot autonomy. Semantic segmentation is one of the key scene understanding tasks which is pivotal for several robotics applications including autonomous driving, domestic service…

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…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices…

There is abundant evidence of the fact that the way words change their meaning can be classified in different types of change, highlighting the relationship between the old and new meanings (among which generalization, specialization and…

Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should exactly match their hypernyms in the description, while the…

Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task,…

Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available. However, deep learning solely focuses on the accuracy of the predictions, neglecting the reasoning process…

Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly detection for image classification, anomaly detection on…

Deep learning is a type of machine learning that adapts a deep hierarchy of concepts. Deep learning classifiers link the most basic version of concepts at the input layer to the most abstract version of concepts at the output layer, also…

Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…

We tackle the problem of robust novelty detection, where we aim to detect novelties in terms of semantic content while being invariant to changes in other, irrelevant factors. Specifically, we operate in a setup with multiple environments,…

Scientific discovery is a cumulative process and requires new ideas to be situated within an ever-expanding landscape of existing knowledge. An emerging and critical challenge is how to identify conceptually relevant prior work from rapidly…

Class-incremental semantic image segmentation assumes multiple model updates, each enriching the model to segment new categories. This is typically carried out by providing expensive pixel-level annotations to the training algorithm for all…

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…

State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel'…

Despite the advances made in visual object recognition, state-of-the-art deep learning models struggle to effectively recognize novel objects in a few-shot setting where only a limited number of examples are provided. Unlike humans who…

Rumour detection is hard because the most accurate systems operate retrospectively, only recognizing rumours once they have collected repeated signals. By then the rumours might have already spread and caused harm. We introduce a new…

Remote sensing image semantic change detection is a method used to analyze remote sensing images, aiming to identify areas of change as well as categorize these changes within images of the same location taken at different times.…

In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but…