A review of generalized zero-shot learning methods
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples
under the condition that some output classes are unknown during supervised learning. To …
under the condition that some output classes are unknown during supervised learning. To …
Attribute-modulated generative meta learning for zero-shot learning
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically
related unseen classes, which are absent during training. The promising strategies for ZSL …
related unseen classes, which are absent during training. The promising strategies for ZSL …
Boosting zero-shot learning via contrastive optimization of attribute representations
Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training
set. One representative solution is to directly learn an embedding function associating visual …
set. One representative solution is to directly learn an embedding function associating visual …
An entropy-guided reinforced partial convolutional network for zero-shot learning
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to
unseen classes via semantic correlations. A promising strategy is to learn a global-local …
unseen classes via semantic correlations. A promising strategy is to learn a global-local …
Continual learning in cross-modal retrieval
Multimodal representations and continual learning are two areas closely related to human
intelligence. The former considers the learning of shared representation spaces where …
intelligence. The former considers the learning of shared representation spaces where …
Implicit and explicit attention mechanisms for zero-shot learning
Abstract Zero-Shot Learning (ZSL) aims to recognise unseen object classes which are not
observed during the training phase. Most of the existing methods on ZSL focus on learning a …
observed during the training phase. Most of the existing methods on ZSL focus on learning a …
Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
J Feinglass, JJ Thiagarajan… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base
models which consider only a single class attribute vector representation over the entire …
models which consider only a single class attribute vector representation over the entire …
Rethinking attribute localization for zero-shot learning
Recent advancements in attribute localization have showcased its potential in discovering
the intrinsic semantic knowledge for visual feature representations, thereby facilitating …
the intrinsic semantic knowledge for visual feature representations, thereby facilitating …
Rethink, revisit, revise: A spiral reinforced self-revised network for zero-shot learning
Current approaches to zero-shot learning (ZSL) struggle to learn generalizable semantic
knowledge capable of capturing complex correlations. Inspired by Spiral Curriculum, which …
knowledge capable of capturing complex correlations. Inspired by Spiral Curriculum, which …
Diversity-boosted generalization-specialization balancing for zero-shot learning
Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen
classes. Recent methods have proved that generalization and specialization are two …
classes. Recent methods have proved that generalization and specialization are two …