With the growing interest in pretrained vision-language models like CLIP, recent research
has focused on adapting these models to downstream tasks. Despite achieving promising …

Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic
knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute …

Abstract Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge
transferred from the seen domain, relying on the intrinsic interactions between visual and …

Hazy images captured under ill-posed scenarios with scattering medium (ie haze, fog, or
smoke) are contaminated in visibility. Inevitably, these images are further degraded by …

Compound fault diagnosis of bearings has always been a challenge, due to the occurrence
of various faults with randomness and complexity. Existing deep learning-based methods …

Zero-shot learning models achieve remarkable results on image classification for samples
from classes that were not seen during training. However, such models must be trained from …

Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never
appeared during training. One of the most effective and widely used semantic information for …

Abstract Knowledge distillation is a simple yet effective technique for deep model
compression, which aims to transfer the knowledge learned by a large teacher model to a …

It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain
shift, where the true and learned data distributions for the unseen classes do not match …

Recent zero-shot learning (ZSL) approaches have integrated fine-grained analysis, ie, fine-
grained ZSL, to mitigate the commonly known seen/unseen domain bias and misaligned …