# Evolving Semantic Prototype Improves Generative Zero-Shot Learning

arXiv: https://arxiv.org/abs/2306.06931 · HTML: https://mlsanity.com/paper/2306.06931/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Evaluation of Output Embeddings for Fine-Grained Image Classification](https://mlsanity.com/paper/1409.8403/) (2014)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [Generalized Zero-Shot Learning via Synthesized Examples](https://mlsanity.com/paper/1712.03878/) (2017)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Multi-modal Cycle-consistent Generalized Zero-Shot Learning](https://mlsanity.com/paper/1808.00136/) (2018)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning](https://mlsanity.com/paper/2007.09549/) (2020)
- [Semantic-Guided Multi-Attention Localization for Zero-Shot Learning](https://mlsanity.com/paper/1903.00502/) (2019)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [Transductive Multi-view Zero-Shot Learning](https://mlsanity.com/paper/1501.04560/) (2015)
- [Invertible Zero-Shot Recognition Flows](https://mlsanity.com/paper/2007.04873/) (2020)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Transductive Zero-Shot Learning with Visual Structure Constraint](https://mlsanity.com/paper/1901.01570/) (2019)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification](https://mlsanity.com/paper/2209.10304/) (2022)
- [Dual Progressive Prototype Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2111.02073/) (2021)

## Built on by (most cited first, 20 of 20)

- [Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2404.07713/) (2024)
- [Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning](https://mlsanity.com/paper/2404.14808/) (2024)
- [ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning](https://mlsanity.com/paper/2406.02929/) (2024)
- [EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning](https://mlsanity.com/paper/2308.09915/) (2023)
- [Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model](https://mlsanity.com/paper/2506.23822/) (2025)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning](https://mlsanity.com/paper/2405.12217/) (2024)
- [Encoding Semantic Priors into the Weights of Implicit Neural Representation](https://mlsanity.com/paper/2406.04178/) (2024)
- [PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning](https://mlsanity.com/paper/2410.11560/) (2024)
- [Visual-Semantic Graph Matching Net for Zero-Shot Learning](https://mlsanity.com/paper/2411.11351/) (2024)
- [RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognition](https://mlsanity.com/paper/2505.17501/) (2025)
- [MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2503.06847/) (2025)
- [Characterizing Nonlinear Dynamics via Smooth Prototype Equivalences](https://mlsanity.com/paper/2503.10336/) (2025)
- [Interpretable Zero-shot Learning with Infinite Class Concepts](https://mlsanity.com/paper/2505.03361/) (2025)
- [Class Similarity-Based Multimodal Classification under Heterogeneous Category Sets](https://mlsanity.com/paper/2506.09745/) (2025)
- [Prototype-Guided Curriculum Learning for Zero-Shot Learning](https://mlsanity.com/paper/2508.07771/) (2025)
- [Fine-Grained Zero-Shot Learning with Attribute-Centric Representations](https://mlsanity.com/paper/2512.12219/) (2025)
- [ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learning](https://mlsanity.com/paper/2602.12401/) (2026)
- [Learning Adaptive and Visually Aligned Conditions for Generative Zero-Shot Learning](https://mlsanity.com/paper/2603.06281/) (2026)
- [Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cues](https://mlsanity.com/paper/2603.21138/) (2026)

## Abstract (arXiv)

In zero-shot learning (ZSL), generative methods synthesize class-related sample features based on predefined semantic prototypes. They advance the ZSL performance by synthesizing unseen class sample features for better training the classifier. We observe that each class's predefined semantic prototype (also referred to as semantic embedding or condition) does not accurately match its real semantic prototype. So the synthesized visual sample features do not faithfully represent the real sample features, limiting the classifier training and existing ZSL performance. In this paper, we formulate this mismatch phenomenon as the visual-semantic domain shift problem. We propose a dynamic semantic prototype evolving (DSP) method to align the empirically predefined semantic prototypes and the real prototypes for class-related feature synthesis. The alignment is learned by refining sample features and semantic prototypes in a unified framework and making the synthesized visual sample features approach real sample features. After alignment, synthesized sample features from unseen classes are closer to the real sample features and benefit DSP to improve existing generative ZSL methods by 8.5%, 8.0%, and 9.7% on the standard CUB, SUN AWA2 datasets, the significant performance improvement indicates that evolving semantic prototype explores a virgin field in ZSL.