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

Xiang, Haitao; Xie, Cheng; Zeng, Ting; Ye, Yun

doi:10.48550/arxiv.2102.11566

Cited by 3 publications

(4 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where β is the weighting factor. Since then, the conditional GAN (CGAN) has been combined with different strategies to generative discriminative visual features for the unseen classes, including optimal transport-based approach [142], TFGNSCS [143] which is an extended version of f-CLSWGAN that considers transfer information, meta-learning approach [111] which is based on model-agnostic meta-learning [144], LisGAN [145] which focuses on extracting information from soul samples, SP-GAN [146] which devises a similarity preserving loss with classification loss, Semantic rectifying GAN (SR-GAN) [147] which employs the semantic rectifying network (SRN) [148] to rectify features, CIZSL [149] which is inspired by the human creativity process [150], MGA-GAN [151] which uses multi-graph similarity, and MKFNet-NFG [152] which is adaptive fusion module based on the attention mechanism. Xie et al [153] proposed cross knowledge learning and taxonomy regularization to train more relevant semantic features and generalized visual features, respectively.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah

Abdar

Luo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

131

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: Generative Adversarial Networkmentioning

confidence: 99%

A Review of Generalized Zero-Shot Learning Methods

Pourpanah

Abdar

Luo

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

131

View full text Add to dashboard Cite

show abstract

“…For example, the class jumping represents the action of individuals propelling themselves off the ground using both feet. GZSAR enables models to adapt to new action classes without extensive retraining or fine-tuning [10], [11]. Secondly, the increasing number of classes makes collecting labeled data for each category more challenging because models have to distinguish among more classes some of which can be quite similar.…”

Section: Introductionmentioning

confidence: 99%

“…Secondly, the increasing number of classes makes collecting labeled data for each category more challenging because models have to distinguish among more classes some of which can be quite similar. GZSAR models can recognize new classes without the need for additional labeled data [10], [11]. Thirdly, GZSAR reduces the dependency on large volumes of labeled data, resulting in more efficient training processes and decreased computational resource demands [10], [11].…”

Section: Introductionmentioning

confidence: 99%

“…GZSAR models can recognize new classes without the need for additional labeled data [10], [11]. Thirdly, GZSAR reduces the dependency on large volumes of labeled data, resulting in more efficient training processes and decreased computational resource demands [10], [11]. Lastly, GZSAR models exhibit enhanced adaptability to new domains or contexts, increasing their versatility and robustness [10], [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalized Zero-Shot Learning for Action Recognition Fusing Text and Image GANs

Huang,

Mckeever,

Miralles-Pechuán

2024

IEEE Access

View full text Add to dashboard Cite

Generalized Zero-Shot Action Recognition (GZSAR) is geared towards recognizing classes that the model has not been trained on, while still maintaining robust performance on the familiar, trained classes. This approach mitigates the need for an extensive amount of labeled training data and enhances the efficient utilization of available datasets. The main contribution of this paper is a novel approach for GZSAR that combines the power of two Generative Adversarial Networks (GANs). One GAN is responsible for generating embeddings from visual representations, while the other GAN focuses on generating embeddings from textual representations. These generated embeddings are fused, with the selection of the maximum value from each array that represents the embeddings, and this fused data is then utilized to train a GZSAR classifier in a supervised manner. This framework also incorporates a feature refinement component and an out-of-distribution detector to mitigate the domain shift problem between seen and unseen classes. In our experiments, notable improvements were observed. On the UCF101 benchmark dataset, we achieved a 7.43% increase in performance, rising from 50.93% (utilizing images and Word2Vec alone) to 54.71% with the implementation of two GANs. Additionally, on the HMDB51 dataset, we saw a 7.06% improvement, advancing from 36.11% using Text and Word2Vec to 38.66% with the dual-GAN approach. These results underscore the efficacy of our dual-GAN framework in enhancing GZSAR performance. The rest of the paper shows the main contributions to the field of GZSAR and highlights the potential and future lines of research in this exciting area.

show abstract

A Review of Generalized Zero-Shot Learning Methods

Pourpanah¹,

Abdar²,

Luo³

et al. 2020

Preprint

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 both 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 of GZSL. Firstly, we provide an overview of GZSL including the problems and challenging issues. Then, we introduce a hierarchical categorization of the GZSL methods and discuss the representative methods of each category. In addition, we discuss several research directions for future studies.

show abstract

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

Cited by 3 publications

References 62 publications

A Review of Generalized Zero-Shot Learning Methods

A Review of Generalized Zero-Shot Learning Methods

Generalized Zero-Shot Learning for Action Recognition Fusing Text and Image GANs

A Review of Generalized Zero-Shot Learning Methods

Contact Info

Product

Resources

About