PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning
Not on the map. Why?
Abstract (arXiv)
Generalized zero-shot learning (GZSL) endeavors to identify the unseen categories using knowledge from the seen domain, necessitating the intrinsic interactions between the visual features and attribute semantic features. However, GZSL suffers from insufficient visual-semantic correspondences due to the attribute diversity and instance diversity. Attribute diversity refers to varying semantic granularity in attribute descriptions, ranging from low-level (specific, directly observable) to high-level (abstract, highly generic) characteristics. This diversity challenges the collection of adequate visual cues for attributes under a uni-granularity. Additionally, diverse visual instances corresponding to the same sharing attributes introduce semantic ambiguity, leading to vague visual patterns. To tackle these problems, we propose a multi-granularity progressive semantic-visual mutual adaption (PSVMA+) network, where sufficient visual elements across granularity levels can be gathered to remedy the granularity inconsistency. PSVMA+ explores semantic-visual interactions at different granularity levels, enabling awareness of multi-granularity in both visual and semantic elements. At each granularity level, the dual semantic-visual transformer module (DSVTM) recasts the sharing attributes into instance-centric attributes and aggregates the semantic-related visual regions, thereby learning unambiguous visual features to accommodate various instances. Given the diverse contributions of different granularities, PSVMA+ employs selective cross-granularity learning to leverage knowledge from reliable granularities and adaptively fuses multi-granularity features for comprehensive representations. Experimental results demonstrate that PSVMA+ consistently outperforms state-of-the-art methods.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 45 of its 67 references that are in the map. First posted on arXiv 15 Oct 2024.
Builds on
45 of 67 references.
References · 45
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
- 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
33 more
- 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
- 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
- 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
- 2016Latent Embeddings for Zero-shot Classificationcited by 129
- 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
- 2022Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encodingcited by 83
- 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
- 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
- 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
- 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
- 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
- 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
- 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
- 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 53
- 2020Invertible Zero-Shot Recognition Flowscited by 48
- 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
- 2022DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learningcited by 33
- 2016Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learningcited by 30
- 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
- 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
- 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
- 2018Discriminative Learning of Latent Features for Zero-Shot Recognitioncited by 24
- 2023Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learningcited by 24
- 2023Evolving Semantic Prototype Improves Generative Zero-Shot Learningcited by 20
- 2022Attribute Prototype Network for Any-Shot Learningcited by 19
- 2018Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learningcited by 15
- 2021Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learningcited by 12
- 2021Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learningcited by 8
- 2019On zero-shot recognition of generic objectscited by 6
- 2020Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognitioncited by 6
- 2021Implicit and Explicit Attention for Zero-Shot Learningcited by 5
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.