English(EN) Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

自适应赫布路由增强了少样本视觉 Transformer 的性能

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-23 16:16

研究人员为少样本视觉 Transformer 开发了一种自适应赫布记忆路由方法，以提高从有限数据中进行图像识别的能力。该方法使用轻量级 MLP 路由器来动态控制赫布记忆的贡献、更新强度和先前记忆的保留。在各种骨干网络和数据集上的实验表明，自适应变体与固定的赫布方法相比，提高了性能并缩短了推理时间，显示了自适应可塑性和记忆激活的好处。 AI

影响提高了在有限数据集上训练的图像识别模型的效率和准确性。

排序理由该集群包含一篇详细介绍计算机视觉少样本学习新方法的 ist 研究论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Mohammed Yusuf Mujawar, Noorbakhsh Amiri Golilarz · 2026-06-24 04:00

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

arXiv:2606.24756v1 Announce Type: new Abstract: Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary associative information during an episode, but fixed memory behavior may not be ap…
arXiv cs.CV TIER_1 English(EN) · Noorbakhsh Amiri Golilarz · 2026-06-23 16:16

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary associative information during an episode, but fixed memory behavior may not be appropriate for every few-shot task. In this work,…

报道来源 [2]

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

相关实体

相关话题