Fine-grained zero-shot learning: Advances, challenges, and prospects

J Guo, Z Rao, Z Chen, J Zhou, D Tao - arxiv preprint arxiv:2401.17766, 2024 - arxiv.org
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 …

Msdn: Mutually semantic distillation network for zero-shot learning

S Chen, Z Hong, GS **e, W Yang… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …

Zero-shot referring image segmentation with global-local context features

S Yu, PH Seo, J Son - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Referring image segmentation (RIS) aims to find a segmentation mask given a referring
expression grounded to a region of the input image. Collecting labelled datasets for this …

Progressive semantic-visual mutual adaption for generalized zero-shot learning

M Liu, F Li, C Zhang, Y Wei, H Bai… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge
transferred from the seen domain, relying on the intrinsic interactions between visual and …

A zero-shot fault semantics learning model for compound fault diagnosis

J Xu, S Liang, X Ding, R Yan - Expert Systems with Applications, 2023 - Elsevier
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 …

Hybrid routing transformer for zero-shot learning

D Cheng, G Wang, B Wang, Q Zhang, J Han… - Pattern Recognition, 2023 - Elsevier
Zero-shot learning (ZSL) aims to learn models that can recognize unseen image semantics
based on the training of data with seen semantics. Recent studies either leverage the global …

Intra-modal proxy learning for zero-shot visual categorization with clip

Q Qian, Y Xu, J Hu - Advances in Neural Information …, 2023 - proceedings.neurips.cc
Vision-language pre-training methods, eg, CLIP, demonstrate an impressive zero-shot
performance on visual categorizations with the class proxy from the text embedding of the …

Duet: Cross-modal semantic grounding for contrastive zero-shot learning

Z Chen, Y Huang, J Chen, Y Geng, W Zhang… - Proceedings of the …, 2023 - ojs.aaai.org
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 …

Improving zero-shot generalization for clip with variational adapter

Z Lu, F Shen, M Liu, Y Yu, X Li - European Conference on Computer …, 2024 - Springer
The excellent generalization capability of pre-trained Vision-Language Models (VLMs)
makes fine-tuning VLMs for downstream zero-shot tasks a popular choice. Despite …

Learning adversarial semantic embeddings for zero-shot recognition in open worlds

T Li, G Pang, X Bai, J Zheng, L Zhou, X Ning - Pattern Recognition, 2024 - Elsevier
Abstract Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with
only their side semantic information presented during training. It cannot handle real-life …