# Few-Shot Inspired Generative Zero-Shot Learning

arXiv: https://arxiv.org/abs/2507.01026 · HTML: https://mlsanity.com/paper/2507.01026/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 53 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [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)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [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)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [Zero-Shot Learning via Semantic Similarity Embedding](https://mlsanity.com/paper/1509.04767/) (2015)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Transferable Contrastive Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1908.05832/) (2019)
- [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)
- [Generalized Zero-Shot Learning Via Over-Complete Distribution](https://mlsanity.com/paper/2004.00666/) (2020)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Preserving Semantic Relations for Zero-Shot Learning](https://mlsanity.com/paper/1803.03049/) (2018)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning](https://mlsanity.com/paper/1810.08332/) (2018)
- [Synthetic Sample Selection for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2304.02846/) (2023)
- [Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2108.00045/) (2021)
- [Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis](https://mlsanity.com/paper/2203.05335/) (2022)
- [Semantic Feature Extraction for Generalized Zero-shot Learning](https://mlsanity.com/paper/2112.14478/) (2021)
- [Zero-Shot Learning by Generating Pseudo Feature Representations](https://mlsanity.com/paper/1703.06389/) (2017)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [Zero-Shot Learning posed as a Missing Data Problem](https://mlsanity.com/paper/1612.00560/) (2016)

## Abstract (arXiv)

Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require substantial computational resources and extensive synthetic data, thereby relaxing the original ZSL assumptions. In this paper, we propose FSIGenZ, a few-shot-inspired generative ZSL framework that reduces reliance on large-scale feature synthesis. Our key insight is that class-level attributes exhibit instance-level variability, i.e., some attributes may be absent or partially visible, yet conventional ZSL methods treat them as uniformly present. To address this, we introduce Model-Specific Attribute Scoring (MSAS), which dynamically re-scores class attributes based on model-specific optimization to approximate instance-level variability without access to unseen data. We further estimate group-level prototypes as clusters of instances based on MSAS-adjusted attribute scores, which serve as representative synthetic features for each unseen class. To mitigate the resulting data imbalance, we introduce a Dual-Purpose Semantic Regularization (DPSR) strategy while training a semantic-aware contrastive classifier (SCC) using these prototypes. Experiments on SUN, AwA2, and CUB benchmarks demonstrate that FSIGenZ achieves competitive performance using far fewer synthetic features.