Related papers: Cluster-based Zero-shot learning for multivariate …

Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world. While considerable progress…

Zero-shot learning (ZSL) models rely on learning a joint embedding space where both textual/semantic description of object classes and visual representation of object images can be projected to for nearest neighbour search. Despite the…

This paper tackles the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign classes to recognize the instances of unseen sign classes. In this context, readily available…

Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by…

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the…

Machine learning especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for supervision. As sufficient labeled training data are not always ready due to e.g., continuously…

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…

Zero-shot learning (ZSL) aims at recognizing unseen class examples (e.g., images) with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space shared by both seen and unseen classes, e.g.,…

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and…

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing…

Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero-Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall…

Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are trained on these synthetic data in a supervised manner. In…

The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet…

Zero-Shot Learning (ZSL) has received extensive attention and successes in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. Key to ZSL is to transfer knowledge from the seen to the unseen…

Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR).…

A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive…

Zero-shot learning (ZSL) has received extensive attention recently especially in areas of fine-grained object recognition, retrieval, and image captioning. Due to the complete lack of training samples and high requirement of defense…

To overcome the absence of training data for unseen classes, conventional zero-shot learning approaches mainly train their model on seen datapoints and leverage the semantic descriptions for both seen and unseen classes. Beyond exploiting…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often favoring the classes…