Nothing Special   »   [go: up one dir, main page]

×
Please click here if you are not redirected within a few seconds.
In this paper, we propose a Salient Attributes Learning Network (SALN) for generalized zero-shot learning. SALN can generate more discriminative semantic ...
People also ask
The performance of the proposed approach has made progress on the five benchmark datasets in generalized zero-shot learning task, and in-depth experiments ...
The goal for ZSL is to predict the label of images from unseen classes, i.e., X →Yu, while for generalized ZSL (GZSL). [42] the goal is to predict images from ...
Apr 12, 2024 · Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector ...
Dec 2, 2023 · We propose a Meta-learned Attribute self-Interaction Network (MAIN) for continual ZSL. By pairing attribute self-interaction trained using meta-learning with ...
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled ...
Many approaches in Generalized Zero-Shot Learning. (GZSL) are built upon base models which consider only a single class attribute vector representation over ...
Summary and Contributions: This paper proposes an attribute prototype network for zero-shot learning which improves local representations.
A novel zero-shot representation learning framework that jointly learns discriminative global and local features using only class-level attributes and ...
Attributes learning network for generalized zero-shot learning. https://doi.org/10.1016/j.neunet.2022.02.018 ·. Journal: Neural Networks, 2022, p. 112-118.