Generalized Zero-Shot Learning
41 papers with code • 10 benchmarks • 8 datasets
Suffering from the extreme training data imbalance between seen and unseen classes, most of existing state-of-the-art approaches fail to achieve satisfactory results for the challenging generalized zero-shot learning task.
Normalization techniques have proved to be a crucial ingredient of successful training in a traditional supervised learning regime.
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.
In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions.
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples.
Using a gating mechanism that discriminates the unseen samples from the seen samples can decompose the GZSL problem to a conventional Zero-Shot Learning (ZSL) problem and a supervised classification problem.
In constrast, Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) tasks inherently lack supervision across all classes.
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
Zero-shot learning (ZSL) methods have been studied in the unrealistic setting where test data are assumed to come from unseen classes only.
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes.