Fine-grained zero-shot learning: Advances, challenges, and prospects
Recent zero-shot learning (ZSL) approaches have integrated fine-grained analysis, ie, fine-
grained ZSL, to mitigate the commonly known seen/unseen domain bias and misaligned …
grained ZSL, to mitigate the commonly known seen/unseen domain bias and misaligned …
Progressive semantic-visual mutual adaption for generalized zero-shot learning
Abstract Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge
transferred from the seen domain, relying on the intrinsic interactions between visual and …
transferred from the seen domain, relying on the intrinsic interactions between visual and …
Learning adversarial semantic embeddings for zero-shot recognition in open worlds
Abstract Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with
only their side semantic information presented during training. It cannot handle real-life …
only their side semantic information presented during training. It cannot handle real-life …
Evolving semantic prototype improves generative zero-shot learning
In zero-shot learning (ZSL), generative methods synthesize class-related sample features
based on predefined semantic prototypes. They advance the ZSL performance by …
based on predefined semantic prototypes. They advance the ZSL performance by …
Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning
Generative Zero-shot learning (ZSL) learns a generator to synthesize visual samples for
unseen classes which is an effective way to advance ZSL. However existing generative …
unseen classes which is an effective way to advance ZSL. However existing generative …
Zero-shot node classification with graph contrastive embedding network
This paper studies zero-shot node classification, which aims to predict new classes (ie,
unseen classes) of nodes in a graph. This problem is challenging yet promising in a variety …
unseen classes) of nodes in a graph. This problem is challenging yet promising in a variety …
Semantic contrastive embedding for generalized zero-shot learning
Generalized zero-shot learning (GZSL) aims to recognize objects from both seen and
unseen classes when only the labeled examples from seen classes are provided. Recent …
unseen classes when only the labeled examples from seen classes are provided. Recent …
Prototypical matching networks for video object segmentation
Semi-supervised video object segmentation is the task of segmenting the target in
sequential frames given the ground truth mask in the first frame. The modern approaches …
sequential frames given the ground truth mask in the first frame. The modern approaches …
Zero-shot learning with common sense knowledge graphs
Zero-shot learning relies on semantic class representations such as hand-engineered
attributes or learned embeddings to predict classes without any labeled examples. We …
attributes or learned embeddings to predict classes without any labeled examples. We …
Part-object progressive refinement network for zero-shot learning
Zero-shot learning (ZSL) recognizes unseen images by sharing semantic knowledge
transferred from seen images, encouraging the investigation of associations between …
transferred from seen images, encouraging the investigation of associations between …