Prototype-Guided Curriculum Learning for Zero-Shot Learning
Not on the map. Why?
Abstract (arXiv)
In Zero-Shot Learning (ZSL), embedding-based methods enable knowledge transfer from seen to unseen classes by learning a visual-semantic mapping from seen-class images to class-level semantic prototypes (e.g., attributes). However, these semantic prototypes are manually defined and may introduce noisy supervision for two main reasons: (i) instance-level mismatch: variations in perspective, occlusion, and annotation bias will cause discrepancies between individual sample and the class-level semantic prototypes; and (ii) class-level imprecision: the manually defined semantic prototypes may not accurately reflect the true semantics of the class. Consequently, the visual-semantic mapping will be misled, reducing the effectiveness of knowledge transfer to unseen classes. In this work, we propose a prototype-guided curriculum learning framework (dubbed as CLZSL), which mitigates instance-level mismatches through a Prototype-Guided Curriculum Learning (PCL) module and addresses class-level imprecision via a Prototype Update (PUP) module. Specifically, the PCL module prioritizes samples with high cosine similarity between their visual mappings and the class-level semantic prototypes, and progressively advances to less-aligned samples, thereby reducing the interference of instance-level mismatches to achieve accurate visual-semantic mapping. Besides, the PUP module dynamically updates the class-level semantic prototypes by leveraging the visual mappings learned from instances, thereby reducing class-level imprecision and further improving the visual-semantic mapping. Experiments were conducted on standard benchmark datasets-AWA2, SUN, and CUB-to verify the effectiveness of our method.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 85 references that are in the map. First posted on arXiv 11 Aug 2025.
Builds on
49 of 85 references.
References · 49
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
- 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
- 2021Curriculum Learning: A Surveycited by 259
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
- 2019Competence-based Curriculum Learning for Neural Machine Translationcited by 202
- 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
- 2015Label-Embedding for Image Classificationcited by 165
37 more
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
- 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
- 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
- 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
- 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
- 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
- 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
- 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
- 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
- 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
- 2017Learning Robust Visual-Semantic Embeddingscited by 56
- 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 54
- 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
- 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
- 2014Zero Shot Recognition with Unreliable Attributescited by 39
- 2022DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learningcited by 33
- 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
- 2016Zero-Shot Visual Recognition via Bidirectional Latent Embeddingcited by 27
- 2020Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patchescited by 27
- 2022VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learningcited by 27
- 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
- 2018Discriminative Learning of Latent Features for Zero-Shot Recognitioncited by 24
- 2016Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learningcited by 22
- 2016Self-Paced Learning: an Implicit Regularization Perspectivecited by 21
- 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
- 2023Evolving Semantic Prototype Improves Generative Zero-Shot Learningcited by 20
- 2022Attribute Prototype Network for Any-Shot Learningcited by 19
- 2019Zero-shot Learning via Simultaneous Generating and Learningcited by 17
- 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
- 2020Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Locationcited by 10
- 2024An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognitioncited by 7
- 2024Visual-Semantic Graph Matching Net for Zero-Shot Learningcited by 3
Built on by
Not cited yet.