Generalized Zero-Shot Learning

49 papers with code • 13 benchmarks • 11 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Feature Generating Networks for Zero-Shot Learning

akku1506/Feature-Generating-Networks-for-ZSL CVPR 2018

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.

Zero-Shot Learning with Common Sense Knowledge Graphs

BatsResearch/zsl-kg 18 Jun 2020

Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples.

Class Normalization for (Continual)? Generalized Zero-Shot Learning

universome/czsl 19 Jun 2020

Normalization techniques have proved to be a crucial ingredient of successful training in a traditional supervised learning regime.

Contrastive Embedding for Generalized Zero-Shot Learning

Hanzy1996/CE-GZSL CVPR 2021

To tackle this issue, we propose to integrate the generation model with the embedding model, yielding a hybrid GZSL framework.

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

edgarschnfld/CADA-VAE-PyTorch 5 Dec 2018

Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.

A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning

Chenxingyu1990/A-Boundary-Based-Out-of-Distribution-Classifier-for-Generalized-Zero-Shot-Learning ECCV 2020

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.

A Deep Dive into Adversarial Robustness in Zero-Shot Learning

MKYucel/adversarial_robustness_zsl 17 Aug 2020

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

pujols/Zero-shot-learning-journal 13 May 2016

Zero-shot learning (ZSL) methods have been studied in the unrealistic setting where test data are assumed to come from unseen classes only.

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

rfelixmg/frwgan-eccv18 ECCV 2018

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.

Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance

ramprs/neuron-importance-zsl ECCV 2018

Our approach, which we call Neuron Importance-AwareWeight Transfer (NIWT), learns to map domain knowledge about novel "unseen" classes onto this dictionary of learned concepts and then optimizes for network parameters that can effectively combine these concepts - essentially learning classifiers by discovering and composing learned semantic concepts in deep networks.