Zero-shot image classification - Open Access .click

Lecture Notes in Computer Science, 2021
Document image classification is one of the most important components in business automation workflow. Therefore, a range of different supervised image classification methods have been proposed, which rely on a large amount of labeled data, which is rarely available in practice. Furthermore, retraining of these models is necessary upon the introduction
Sheraz Ahmed +2 more
exaly +2 more sources

Multimodal Ensembling for Zero-Shot Image Classification

Proceedings of the AAAI Conference on Artificial Intelligence
Artificial intelligence has made significant progress in image classification, an essential task for machine perception to achieve human-level image understanding. Despite recent advances in vision-language fields, multimodal image classification is still challenging, particularly for the following two reasons.
Hickmon, Javon
openaire +3 more sources

Deep Ranking for Image Zero-Shot Multi-Label Classification

IEEE Transactions on Image Processing, 2020
During the past decade, both multi-label learning and zero-shot learning have attracted huge research attention, and significant progress has been made. Multi-label learning algorithms aim to predict multiple labels given one instance, while most existing zero-shot learning approaches target at predicting a single testing label for each unseen class ...
Zhong Ji +6 more
openaire +4 more sources

zero-shot learning
fos: computer and information sciences
computer vision and pattern recognition cs.cv

deep learning
machine learning cs.lg
computer science - machine learning

image classification
zero-shot classification
computer vision and pattern recognition