# Learning Adaptive and Visually Aligned Conditions for Generative Zero-Shot Learning

arXiv: https://arxiv.org/abs/2603.06281 · HTML: https://mlsanity.com/paper/2603.06281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Learning Deep Representations of Fine-grained Visual Descriptions](https://mlsanity.com/paper/1605.05395/) (2016)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [Learning a Deep Embedding Model for Zero-Shot Learning](https://mlsanity.com/paper/1611.05088/) (2016)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Improving Zero-Shot Generalization for CLIP with Synthesized Prompts](https://mlsanity.com/paper/2307.07397/) (2023)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Evolving Semantic Prototype Improves Generative Zero-Shot Learning](https://mlsanity.com/paper/2306.06931/) (2023)
- [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)
- [GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder](https://mlsanity.com/paper/2505.11882/) (2025)
- [Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2503.23030/) (2025)
- [PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning](https://mlsanity.com/paper/2410.11560/) (2024)

## Abstract (arXiv)

Generative zero-shot learning (ZSL) synthesizes visual features for unseen classes by learning a semantic-conditioned generator from seen classes. Since semantic conditions determine the knowledge transfer from seen to unseen classes, their effectiveness is critical for generating plausible features. However, existing class-level semantic prototypes lack semantic diversity to capture intra-class variations, while exhibiting inconsistent inter-class structures with the visual space due to the semantic-visual gap. To address these issues, we propose Adaptive Attribute Distribution and Visual Structure Alignment (AAVS), a unified semantic condition learning framework for generative ZSL. Specifically, the Adaptive Attribute Distribution (AAD) learns dimension-adaptive attribute distributions with discriminability-guided variation calibration to capture transferable semantic diversity, while Visual Structure Alignment (VSA) aligns the diverse attributes with refined visual prototypes to learn visual inter-class structures. By jointly modeling semantic diversity and visual structural consistency, AAVS provides more effective generation conditions for unseen classes to generate visual features. Extensive quantitative and qualitative evaluations on three benchmarks demonstrate that AAVS outperforms existing generative ZSL methods and validate the effectiveness of the learned generation conditions.