Related papers: Revisiting Document Representations for Large-Scal…

Zero-shot learning (ZSL) highly depends on a good semantic embedding to connect the seen and unseen classes. Recently, distributed word embeddings (DWE) pre-trained from large text corpus have become a popular choice to draw such a…

Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples. We propose to learn class representations by embedding nodes from common…

Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of…

Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained…

Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs.…

The problem of organizing and finding images in a user's directory has become increasingly challenging due to the rapid growth in the number of images captured on personal devices. This paper presents a solution that utilizes zero shot…

Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating categories with their semantic information like attributes.…

In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to…

Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize unseen classes without labeled training data by exploiting semantic information, which contains knowledge between seen and unseen classes. Existing ZSL…

Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding…

We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…

Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt to associate the…

Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent paradigm called transductive zero-shot learning further leverages…

Despite the tremendous progress in zero-shot learning(ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale. An unsupervised alternative is to represent each class using…

Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…

Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training set. One representative solution is to directly learn an embedding function associating visual features with corresponding class semantics for…

We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic…

Zero-shot recognition aims to accurately recognize objects of unseen classes by using a shared visual-semantic mapping between the image feature space and the semantic embedding space. This mapping is learned on training data of seen…

To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…

Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable.…