Hebbian Fast Weights enhance Vision Transformers for few-shot character recognition

Researchers have developed a new approach to few-shot character recognition by integrating Hebbian Fast-Weight (HFW) modules into Vision Transformer architectures. This method aims to mimic biological neural systems' ability to form transient associative memories during inference, unlike standard transformers that rely on fixed representations. When applied to a Swin-Tiny model, this strategy achieved a 96.2% accuracy in 5-way 1-shot classification and 99.2% in 5-way 5-shot classification on the Omniglot benchmark, slightly outperforming its non-Hebbian counterpart. AI

影响 Introduces a novel method for few-shot learning that could improve model adaptability in low-data scenarios.

排序理由 This is a research paper presenting a novel method for few-shot learning in computer vision. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• DeiT-Small
• Hebbian Fast-Weight
• Omniglot
• Swin-Tiny
• Vision Transformer
• ViT-Small

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →