Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes. They have been …
In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to …
Deep learning-based models have been shown to outperform human beings in many computer vision tasks with massive available labeled training data in learning. However …
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To …
Z Han, Z Fu, S Chen, J Yang - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and unseen classes, when only the labeled examples from seen classes are provided. Recent …
Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gaps and seen-unseen …
Recent developments in multimodal training methodologies, including CLIP and ALIGN, obviate the necessity for individual data labeling. These approaches utilize pairs of data and …
The key challenge of zero-shot learning (ZSL) is how to infer the latent semantic knowledge between visual and attribute features on seen classes, and thus achieving a desirable …
We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open- Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by …