Decomposed soft prompt guided fusion enhancing for compositional zero-shot learning

X Lu, S Guo, Z Liu, J Guo - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Abstract Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts
formed by known states and objects during training. Existing methods either learn the …

Data distribution distilled generative model for generalized zero-shot recognition

Y Wang, M Hong, L Huangfu, S Huang - Proceedings of the AAAI …, 2024 - ojs.aaai.org
In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot
Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to …

[PDF][PDF] Parsnets: A parsimonious composition of orthogonal and low-rank linear networks for zero-shot learning

J Guo, Q Zhou, X Lu, R Li, Z Liu, J Zhang, B Han… - Proceedings of the Thirty …, 2024 - ijcai.org
This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL),
dubbed ParsNets, in which we are interested in learning a composition of on-device friendly …

Mdenet: multi-modal dual-embedding networks for malware open-set recognition

J Guo, Y Xu, W Xu, Y Zhan, Y Sun, S Guo - arxiv preprint arxiv …, 2023 - arxiv.org
Malware open-set recognition (MOSR) aims at jointly classifying malware samples from
known families and detect the ones from novel unknown families, respectively. Existing …