Attribute-Modulated Generative Meta Learning for Zero-Shot Learning

Liu, Xinyi; Liu, Zhe; Yao, Lina; Chang, Xiaojun

doi:10.1109/tmm.2021.3139211

Cited by 28 publications

(12 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different tasks are trained by randomly selecting the classes from both the support and query sets. This mechanism helps meta learning methods to transfer knowledge from the seen to unseen classes, therefore alleviating the bias problem [113].…”

Section: Meta Learning-based Methodsmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah

Abdar

Luo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

128

View full text Add to dashboard Cite

Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of the seen (source) and unseen (target) classes to bridge the gap between both seen and unseen classes. Since its introduction, many GZSL models have been formulated. In this review paper, we present a comprehensive review on GZSL. Firstly, we provide an overview of GZSL including the problems and challenges. Then, we introduce a hierarchical categorization for the GZSL methods and discuss the representative methods in each category. In addition, we discuss the available benchmark data sets and applications of GZSL, along with a discussion on the research gaps and directions for future investigations.

show abstract

Section: Meta Learning-based Methodsmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah

Abdar

Luo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

128

View full text Add to dashboard Cite

show abstract

“…Differently, to enhance the discriminability on both seen and unseen domains, Zhang et al [49] developed a systematical solution via separately learning visual prototypes and proposed an efficient solution. To mitigate biases towards seen classes and accommodate diverse tasks, Li et al [50] proposed an attribute-aware modulation network to remedy the defect of meta generative approaches, which is devoted to explore the common model shared across task distributions. Similarily, Min et al [51] proposed dual-cycle consistency and domain division constraints to make obtain the domain similarity and specialities to overcome biases.…”

Section: B Zero-shot Learningmentioning

confidence: 99%

Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention

Liu¹,

Guo²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several major classes while neglect most of the minor classes with the same importance in input samples, and may thus result in overly diffused attention maps that cannot sufficiently cover minor classes. We argue that disregarding the connection between major and minor classes, i.e., correspond to the global and local information, respectively, is the cause of the problem. In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier. Specifically, Pyramid Feature Attention (PFA) is proposed to build the correlation between global and local information of samples to balance the presence of each class. Meanwhile, for the generated semantic representations of input samples, we propose Semantic Attention (SA) to strengthen the element-wise correlation among these vectors, which can encourage the coordinated representation of them. Extensive experiments on the large-scale multi-label zero-shot benchmarks NUS-WIDE and Open-Images demonstrate that the proposed method surpasses other representative methods by significant margins.

show abstract

“…In addition to its application in tinnitus, EEG has also attracted much attention in other fields, where advanced deep learning methods are used [29], [30], [31], [32]. For example, DeepSleepNet [29] used convolutional neural networks (CNN) and bidirectional-long short-term-memory (LSTM) to automatically score sleep stage based on EEG signals.…”

Section: B Cross-dataset Eeg Research In Related Fieldsmentioning

confidence: 99%

“…In recent years, deep learning has achieved great success in various scenarios, e.g., computer vision [31], [33], natural languages processing [34], [35], applications in health domains [36], [5]. However, the advances in deep learning are based on large-scale datasets(e.g., ImageNet [37]), which is not available in many scenarios of medical applications.…”

Section: Meta-learning Workmentioning

confidence: 99%

Side-aware Meta-Learning for Cross-Dataset Listener Diagnosis with Subjective Tinnitus

Li¹,

Liu²,

Yao³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are datasetspecific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demographic attributes; further, dataset formats may differ, impacting model performance. This paper proposes a side-aware meta-learning for crossdataset tinnitus diagnosis, which can effectively classify tinnitus in subjects of divergent ages and genders from different data collection processes. Owing to the superiority of meta-learning, our method does not rely on large-scale datasets like conventional deep learning models. Moreover, we design a subject-specific training process to assist the model in fitting the data pattern of different patients or healthy people. Our method achieves a high accuracy of 73.8% in the cross-dataset classification. We conduct an extensive analysis to show the effectiveness of side information of ears in enhancing model performance and side-aware metalearning in improving the quality of the learned features.

show abstract

Attribute-Modulated Generative Meta Learning for Zero-Shot Learning

Cited by 28 publications

References 76 publications

A Review of Generalized Zero-Shot Learning Methods

A Review of Generalized Zero-Shot Learning Methods

Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention

Side-aware Meta-Learning for Cross-Dataset Listener Diagnosis with Subjective Tinnitus

Contact Info

Product

Resources

About