A Review of Generalized Zero-Shot Learning Methods

Abstract

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.

arXiv comment26 pages, 12 figures

References in corpus (24)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Transductive Multi-view Zero-Shot Learning
• Graph Learning: A Survey
• Generalized Out-of-Distribution Detection: A Survey
• A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
• SpinalNet: Deep Neural Network with Gradual Input
• Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
• Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review
• Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
• Cluster-based Zero-shot learning for multivariate data
• Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
• Multi-modal Ensemble Classification for Generalized Zero Shot Learning
• From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
• Simple and effective localized attribute representations for zero-shot learning
• Zero-shot Learning via Shared-Reconstruction-Graph Pursuit
• Domain segmentation and adjustment for generalized zero-shot learning
• Transfer feature generating networks with semantic classes structure for zero-shot learning
• From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition
• Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
• Zero-shot Learning with Deep Neural Networks for Object Recognition

Cited by in corpus (24)

• UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection
• Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review
• DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data
• Methods for Class-Imbalanced Learning with Support Vector Machines: A Review and an Empirical Evaluation
• Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
• PaveSAM Segment Anything for Pavement Distress
• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• Visual-Semantic Graph Matching Net for Zero-Shot Learning
• An Ensemble Semi-Supervised Adaptive Resonance Theory Model with Explanation Capability for Pattern Classification
• Contextual Emotion Recognition using Large Vision Language Models
• Region Semantically Aligned Network for Zero-Shot Learning
• Towards Hardware Supported Domain Generalization in DNN-Based Edge Computing Devices for Health Monitoring
• An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
• Segmenting Known Objects and Unseen Unknowns without Prior Knowledge
• BC-MRI-SEG: A Breast Cancer MRI Tumor Segmentation Benchmark
• Improving Significant Wave Height Prediction Using Chronos Models
• Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction
• Multi-modal Learning for WebAssembly Reverse Engineering
• SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning
• On Class Separability Pitfalls In Audio-Text Contrastive Zero-Shot Learning
• Real-Time Super-Resolution Imaging System Based on Zero-Shot Learning for Infrared Non-Destructive Testing
• Direct side information learning for zero-shot regression
• Taking Class Imbalance Into Account in Open Set Recognition Evaluation