Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process. However, the problem of class imbalance is rarely discussed, despite its presence in several ZSL datasets. In this paper, we propose a Neural Network model that learns a latent feature embedding and a Gaussian Process (GP) regression model that predicts latent feature prototypes of unseen classes. A calibrated classifier is then constructed for ZSL and Generalized ZSL tasks. Our Neural Network model is trained efficiently with a simple training strategy that mitigates the impact of class-imbalanced training data. The model has an average training time of 5 minutes and can achieve state-of-the-art (SOTA) performance on imbalanced ZSL benchmark datasets like AWA2, AWA1 and APY, while having relatively good performance on the SUN and CUB datasets.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 11 Oct 2022.
Builds on
33 of 55 references.
References · 33
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2022Generative Adversarial Networkscited by 5,603
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
- 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
21 more
- 2015Label-Embedding for Image Classificationcited by 164
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
- 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
- 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
- 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 90
- 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
- 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
- 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
- 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
- 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
- 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
- 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
- 2020Invertible Zero-Shot Recognition Flowscited by 48
- 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
- 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
- 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
- 2021Isometric Propagation Network for Generalized Zero-shot Learningcited by 18
- 2017Semi-Supervised and Active Few-Shot Learning with Prototypical Networkscited by 8
- 2018From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Processcited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.