Semantics Disentangling for Generalized Zero-Shot Learning

2021-01-20 · ICCV 2021 10 · Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, Zheng Zhang

Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt to associate the visual features of seen classes with attributes or to generate unseen samples directly. Nevertheless, the visual features used in the prior approaches do not necessarily encode semantically related information that the shared attributes refer to, which degrades the model generalization to unseen classes. To address this issue, in this paper, we propose a novel semantics disentangling framework for the generalized zero-shot learning task (SDGZSL), where the visual features of unseen classes are firstly estimated by a conditional VAE and then factorized into semantic-consistent and semantic-unrelated latent vectors. In particular, a total correlation penalty is applied to guarantee the independence between the two factorized representations, and the semantic consistency of which is measured by the derived relation network. Extensive experiments conducted on four GZSL benchmark datasets have evidenced that the semantic-consistent features disentangled by the proposed SDGZSL are more generalizable in tasks of canonical and generalized zero-shot learning. Our source code is available at https://github.com/uqzhichen/SDGZSL.

📄 PDF Abstract BibTeX arXiv:2101.07978

Code (1)

uqzhichen/sdgzsl 공식 구현 pytorch

Tasks

Generalized Zero-Shot LearningRelation NetworkZero-Shot Learning

Semantic Borrowing for Generalized Zero-Shot Learning

2021-01-30 · Xiaowei Chen

Generalized zero-shot learning (GZSL) is one of the most realistic but challenging problems due to the partiality of the classifier to supervised classes, especially under the class-inductive instance-inductive (CIII) tr…

Generalized Zero-Shot Learning Metric Learning zero-shot-classification Zero-Shot Learning

Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning

2022-03-05 · Yi Gao, Chenwei Tang, Jiancheng Lv

Generalized Zero-Shot Learning (GZSL) aims to recognize both seen and unseen classes by training only the seen classes, in which the instances of unseen classes tend to be biased towards the seen class. In this paper, we…

Contrastive Learning Generalized Zero-Shot Learning Zero-Shot Learning

Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning

2019-07-12 · NeurIPS 2019 12 · Jian Ni, Shanghang Zhang, Haiyong Xie

Generalized zero-shot learning (GZSL) is a challenging class of vision and knowledge transfer problems in which both seen and unseen classes appear during testing. Existing GZSL approaches either suffer from semantic los…

Generalized Zero-Shot Learning Transfer Learning Zero-Shot Learning

Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models

2023-10-02 · Zijun Wu, Yongkang Wu, Lili Mou

Prompt tuning in natural language processing (NLP) has become an increasingly popular method for adapting large language models to specific tasks. However, the transferability of these prompts, especially continuous prom…

Multi-Knowledge Fusion for New Feature Generation in Generalized Zero-Shot Learning

2021-02-23 · Hongxin Xiang, Cheng Xie, Ting Zeng, Yun Yang

Suffering from the semantic insufficiency and domain-shift problems, most of existing state-of-the-art methods fail to achieve satisfactory results for Zero-Shot Learning (ZSL). In order to alleviate these problems, we p…

Generalized Zero-Shot Learning Retrieval Zero-Shot Learning