用弱语义向量生成新类别图像，提升零样本学习效果
GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder
- 通过类比人类学习，从已知类推未知类生成样本
- 在AWA2数据集上比f-VAEGAN提升24.7%准确率，训练快60倍以上
- 适合做零样本图像识别的开发者与研究者参考
零样本学习（ZSL）虽在生成模型推动下取得显著进展，但现有方法依赖专家标注的强语义向量生成视觉特征，导致生成性能不足且泛化能力有限。为此，本文提出基于归纳变分自编码器的生成式零样本学习方法GenZSL。该方法通过目标类别名称的弱语义向量（如CLIP文本嵌入）从相似已知类中归纳出新类别样本，模拟人类概念学习。为提升生成样本的有效性，GenZSL引入两类策略：一是增强类别语义向量多样性以促进样本多样性；二是采用目标类别引导的信息增强准则优化模型。在三个主流基准数据集上的大量实验表明，GenZSL在性能与效率上均显著优于f-VAEGAN，例如在AWA2上实现24.7%的性能提升，并保持超过60倍的加速训练速度。代码已开源。
原文摘要 · Abstract (English)
Remarkable progress in zero-shot learning (ZSL) has been achieved using generative models. However, existing generative ZSL methods merely generate (imagine) the visual features from scratch guided by the strong class semantic vectors annotated by experts, resulting in suboptimal generative performance and limited scene generalization. To address these and advance ZSL, we propose an inductive variational autoencoder for generative zero-shot learning, dubbed GenZSL. Mimicking human-level concept learning, GenZSL operates by inducting new class samples from similar seen classes using weak class semantic vectors derived from target class names (i.e., CLIP text embedding). To ensure the generation of informative samples for training an effective ZSL classifier, our GenZSL incorporates two key strategies. Firstly, it employs class diversity promotion to enhance the diversity of class semantic vectors. Secondly, it utilizes target class-guided information boosting criteria to optimize the model. Extensive experiments conducted on three popular benchmark datasets showcase the superiority and potential of our GenZSL with significant efficacy and efficiency over f-VAEGAN, e.g., 24.7% performance gains and more than $60\times$ faster training speed on AWA2. Codes are available at https://github.com/shiming-chen/GenZSL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。