FREE: Feature Refinement for Generalized Zero-Shot Learning

2021-07-29 · ICCV 2021 10 · Shiming Chen, Wenjie Wang, Beihao Xia, Qinmu Peng, Xinge You, Feng Zheng, Ling Shao

Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models trained on ImageNet alone, ignoring the cross-dataset bias between ImageNet and GZSL benchmarks. Such a bias inevitably results in poor-quality visual features for GZSL tasks, which potentially limits the recognition performance on both seen and unseen classes. In this paper, we propose a simple yet effective GZSL method, termed feature refinement for generalized zero-shot learning (FREE), to tackle the above problem. FREE employs a feature refinement (FR) module that incorporates \textit{semantic$\rightarrow$visual} mapping into a unified generative model to refine the visual features of seen and unseen class samples. Furthermore, we propose a self-adaptive margin center loss (SAMC-loss) that cooperates with a semantic cycle-consistency loss to guide FR to learn class- and semantically-relevant representations, and concatenate the features in FR to extract the fully refined features. Extensive experiments on five benchmark datasets demonstrate the significant performance gain of FREE over its baseline and current state-of-the-art methods. Our codes are available at https://github.com/shiming-chen/FREE .

📄 PDF Abstract BibTeX arXiv:2107.13807

Code (1)

shiming-chen/FREE 공식 구현 pytorch

Tasks

Generalized Zero-Shot Learning Zero-Shot Learning

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

2020-06-16 · CVPR 2020 6 · Zongyan Han, Zhen-Yong Fu, Jian Yang

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of different …

Generalized Zero-Shot Learning Object Object Recognition Zero-Shot Learning

Bias-Eliminated Semantic Refinement for Any-Shot Learning

2022-02-10 · Liangjun Feng, Chunhui Zhao, Xi Li

When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen…

Few-Shot Learning Generalized Zero-Shot Learning Generative Adversarial Network Zero-Shot Learning

Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning

2019-03-24 · ICLR Workshop LLD 2019 · Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

Most approaches in generalized zero-shot learning rely on cross-modal mapping between an image feature space and a class embedding space or on generating artificial image features. However, learning a shared cross-modal …

Few-Shot Learning Generalized Zero-Shot Learning Zero-Shot Learning

Data-Free Generalized Zero-Shot Learning

2024-01-28 · Bowen Tang, Long Yan, Jing Zhang, Qian Yu 외

Deep learning models have the ability to extract rich knowledge from large-scale datasets. However, the sharing of data has become increasingly challenging due to concerns regarding data copyright and privacy. Consequent…

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

A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning

2017-06-27 · Shafin Rahman, Salman H. Khan, Fatih Porikli

Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. …

Few-Shot Learning Generalized Zero-Shot Learning One-Shot Learning Zero-Shot Learning