We provide trained models (Google Drive) on three different datasets: CUB, SUN, AWA2 in the CZSL/GZSL setting. You can download model files as well as corresponding datasets, and …

Mar 6, 2013 · We propose a regularization method that can be applied to any conditional generative-based ZSL method, by leveraging only the semantic class prototypes. It learns to …

We select six state-of-the-art ZSL methods, including projection-based methods (ESZSL, SAE, and DEM), and generative methods (f-CLSWGAN, TF-VAEGAN, and CE-GZSL). 📄 Paper: …

To overcome these problems, we propose a Large-scale At-tribute Dataset (LAD) with 78,017 images of 230 classes. 359 attributes of visual, semantic and subjective properties are defined …

The SUN Attribute dataset consists of 14,340 images from 717 scene categories, and each category is annotated with a taxonomy of 102 discriminate attributes. The dataset can be used …

Mar 15, 2025 · Zero-Shot Learning (ZSL) (Sun et al., 2021, Glowacz, 2022, Glowacz, 2023, Feng and Zhao, 2020, Nagy and Czúni, 2022) is primarily designed for recognizing unseen classes …

Mar 1, 2022 · AugMix, for LFGAA + SA (see Fig. 6), introduces improvements in ZSL except some categories, especially on SUN. In the GZSL setting, except SUN, it introduces visible …

In this work, we propose an attention-based model in the problem settings of ZSL to learn attributes useful for unseen class recognition. Our method uses an attention mechanism …

Oct 5, 2019 · We perform experiments on four benchmark ZSL datasets, i.e. Animals with Attributes (AwA) , Caltech-UCSD Birds-200-2011 (CUB-200) , aPascal & aYahoo (aP&Y) , and …

Nov 18, 2018 · In this paper, a unified framework is proposed to combine the above two categories of transductive ZSL models, termed ZSL with superclasses (ZSLS). Specifically, we …