A Review of Generalized Zero-Shot Learning Methods

Pourpanah, Farhad; Abdar, Moloud; Luo, Yuxuan; Zhou, Xinlei; Wang, Ran; Lim, Chee Peng; Wang, Xizhao; Wu, Q. M. Jonathan

doi:10.1109/tpami.2022.3191696

Cited by 163 publications

(57 citation statements)

References 192 publications

(277 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both models use semantic information to help transfer knowledge from seen classes to unseen classes. In an embedding-based model, there are three commonly used embedding spaces, including the semantic vector space, the feature vector space, and the latent space [33]. In our work, we used the scheme of latent space embedding since the feature vector having much noise, and the actual signal is hard to characterize in our semantic space.…”

Section: A Convolutional Neural Network In Ssvep Classificationmentioning

confidence: 99%

A Generalized Zero-Shot Learning Scheme for SSVEP-Based BCI System

Wang

Liu

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

The steady-state visual evoked potential (SSVEP) has been widely used in building multi-target brain-computer interfaces (BCIs) based on electroencephalogram (EEG). However, methods for high-accuracy SSVEP systems require training data for each target, which needs significant calibration time. This study aimed to use the data of only part of the targets for training while achieving high classification accuracy on all targets. In this work, we proposed a generalized zero-shot learning (GZSL) scheme for SSVEP classification. We divided the target classes into seen and unseen classes and trained the classifier only using the seen classes. During the test time, the search space contained both seen classes and unseen classes. In the proposed scheme, the EEG data and the sine waves are embedded into the same latent space using convolutional neural networks (CNN). We use the correlation coefficient of the two outputs in the latent space for classification. Our method was tested on two public datasets and reached 89.9% of the classification accuracy of the state-of-the-art (SOTA) data-driven method, which needs the training data of all targets. Compared to the SOTA training-free method, our method achieved a multifold improvement. This work shows that it is promising to build an SSVEP classification system that does not need the training data of all targets.

show abstract

Section: A Convolutional Neural Network In Ssvep Classificationmentioning

confidence: 99%

A Generalized Zero-Shot Learning Scheme for SSVEP-Based BCI System

Wang

Liu

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…2). Different from the generalized zero-shot learning from image classification [23], our task does not require C train ⊂ C eval , as character sets of different languages may not always show inclusive relations. For example, Japanese and Chinese share some characters in common, but each language has its unique characters.…”

Section: A Problem Formulationmentioning

confidence: 99%

Towards open-set text recognition via label-to-prototype learning

Liu

Yang²,

Qin³

et al. 2023

Pattern Recognition

View full text Add to dashboard Cite

“…This data augmentation strategy can compensate for the lack of training samples of unseen classes and convert ZSL into a supervised classiïňĄcation task. However, they are all complex in structure (not end-to-end) and difficult to train (owing to instability) [46]. The lack of region-attribute supervision data also makes it difficult to accurately understand the corresponding relationship of different attribute-feature pairs during training.…”

Section: Related Work 21 Zero-shot Image Classificationmentioning

confidence: 99%

DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning

Chen¹,

Huang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training, often utilizing additional semantic information (a.k.a. side information) to bridge the training (seen) classes and the unseen classes. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for class-level visual characteristics. However, due to the shortage of fine-grained annotations, the attribute imbalance and co-occurrence, the current methods often fail to discriminate those subtle visual distinctions between images, which limits their performances. In this paper, we present a transformer-based end-to-end ZSL method named DUET, which integrates latent semantic knowledge from the pretrained language models (PLMs) via a self-supervised multi-modal learning paradigm. Specifically, we (1) developed a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images, (2) applied an attribute-level contrastive learning strategy to further enhance the model's discrimination on fine-grained visual characteristics against the attribute co-occurrence and imbalance, and (3) proposed a multi-task learning policy for considering multi-model objectives. With extensive experiments on three standard ZSL benchmarks and a knowledge graph equipped ZSL benchmark, we find that DUET can often achieve state-of-the-art performance, its components are effective and its predictions are interpretable. CCS CONCEPTS• Computing methodologies → Artificial intelligence; Computer vision; Appearance and texture representations.

show abstract

A Review of Generalized Zero-Shot Learning Methods

Cited by 163 publications

References 192 publications

A Generalized Zero-Shot Learning Scheme for SSVEP-Based BCI System

A Generalized Zero-Shot Learning Scheme for SSVEP-Based BCI System

Towards open-set text recognition via label-to-prototype learning

DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning

Contact Info

Product

Resources

About