Related papers: Towards Visual Explainable Active Learning for Zer…
Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…
Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block, and it plays a crucial role in environmental perception. Conventional…
Zero-shot learning in Language & Vision is the task of correctly labelling (or naming) objects of novel categories. Another strand of work in L&V aims at pragmatically informative rather than ``correct'' object descriptions, e.g. in…
The number of categories for action recognition is growing rapidly and it has become increasingly hard to label sufficient training data for learning conventional models for all categories. Instead of collecting ever more data and labelling…
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of ZSL, we model the visual learning process of unseen categories with inspiration…
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings,…
In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions? Existing attribute-based zero-shot classification methods are shown to work poorly in the selective…
This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to…
In this paper we introduce the problem of Visual Semantic Role Labeling: given an image we want to detect people doing actions and localize the objects of interaction. Classical approaches to action recognition either study the task of…
Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architectural adaptations to handle video data, we…
Zero-shot learning (ZSL) which aims to recognize unseen object classes by only training on seen object classes, has increasingly been of great interest in Machine Learning, and has registered with some successes. Most existing ZSL methods…
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class…
In Zero-shot learning (ZSL), we classify unseen categories using textual descriptions about their expected appearance when observed (class embeddings) and a disjoint pool of seen classes, for which annotated visual data are accessible. We…
Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action…
Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the…
Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged…
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves…
While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…
Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…
Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage,…