English

Few-Shot Inspired Generative Zero-Shot Learning

Machine Learning 2025-07-03 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2507.01026,
  title  = {Few-Shot Inspired Generative Zero-Shot Learning},
  author = {Md Shakil Ahamed Shohag and Q. M. Jonathan Wu and Farhad Pourpanah},
  journal= {arXiv preprint arXiv:2507.01026},
  year   = {2025}
}
R2 v1 2026-07-01T03:42:04.872Z