Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis

2022-03-10 · CVPR 2022 1 · Yaogong Feng, Xiaowen Huang, Pengbo Yang, Jian Yu, Jitao Sang

Synthesizing pseudo samples is currently the most effective way to solve the Generalized Zero-Shot Learning (GZSL) problem. Most models achieve competitive performance but still suffer from two problems: (1) Feature confounding, the overall representations confound task-correlated and task-independent features, and existing models disentangle them in a generative way, but they are unreasonable to synthesize reliable pseudo samples with limited samples; (2) Distribution uncertainty, that massive data is needed when existing models synthesize samples from the uncertain distribution, which causes poor performance in limited samples of seen classes. In this paper, we propose a non-generative model to address these problems correspondingly in two modules: (1) Task-correlated feature disentanglement, to exclude the task-correlated features from task-independent ones by adversarial learning of domain adaption towards reasonable synthesis; (2) Controllable pseudo sample synthesis, to synthesize edge-pseudo and center-pseudo samples with certain characteristics towards more diversity generated and intuitive transfer. In addation, to describe the new scene that is the limit seen class samples in the training process, we further formulate a new ZSL task named the 'Few-shot Seen class and Zero-shot Unseen class learning' (FSZU). Extensive experiments on four benchmarks verify that the proposed method is competitive in the GZSL and the FSZU tasks.

📄 PDF Abstract BibTeX arXiv:2203.05335

Code (0)

등록된 구현이 없습니다.

Tasks

Disentanglement Domain Adaptation Generalized Zero-Shot Learning Zero-Shot Learning

Model Selection for Generalized Zero-shot Learning

2018-11-08 · Hongguang Zhang, Piotr Koniusz

In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distribution which mak…

Generalized Zero-Shot Learning Generative Adversarial Network model Model Selection+1

Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning

2021-02-23 · Vinay Kumar Verma, Kevin Liang, Nikhil Mehta, Lawrence Carin

Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generat…

Attribute Generalized Zero-Shot Learning Meta-Learning Zero-Shot Learning

Generative Multi-Label Zero-Shot Learning

2021-01-27 · Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan 외

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized varia…

Attribute Generative Adversarial Network image-classification Image Classification+3

Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition

2024-02-18 · Yijie Wang, Mingjian Hong, Luwen Huangfu, Sheng Huang

In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end generative GZSL framework called D$^3$GZSL. …

Generalized Zero-Shot Learning Zero-Shot Learning

Domain segmentation and adjustment for generalized zero-shot learning

2020-02-01 · Xinsheng Wang, Shanmin Pang, Jihua Zhu

In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. However, this method requ…