Related papers: Text2Model: Text-based Model Induction for Zero-sh…

Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential…

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still very challenging. With an aim towards improving performance…

Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic 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…

Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the…

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically…

Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within…

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…

Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared…

This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…

We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features.…

Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to…

Zero-shot, training-free, image-based text-to-video generation is an emerging area that aims to generate videos using existing image-based diffusion models. Current methods in this space require specific architectural changes to image…

This paper explores the feasibility of using text-to-image models in a zero-shot setup to generate images for taxonomy concepts. While text-based methods for taxonomy enrichment are well-established, the potential of the visual dimension…

We observe that the mapping between an image's representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across diverse models. Building on this observation, we propose…