Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
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, we propose Adaptive Hebbian Routing for few-shot Vision Transformers. The method uses a lightweight MLP router to control the contribution of Hebbian memory, the strength of memory updates, and the retention of previous memory from support-set features. We study Adaptive Placement, Adaptive Plasticity, and Fully Adaptive Hebbian Routing. Experiments use ViT-Small, DeiT-Small, and Swin-Tiny under 5-way 1-shot evaluation on Omniglot, CIFAR-FS, and cross-domain transfer from CIFAR-FS to Omniglot. In the direct Swin comparison, fixed and adaptive Hebbian variants use the same memory location. Adaptive Plasticity improves the fixed Hebbian result from 96.74% to 96.92%, while Fully Adaptive Routing achieves the best result at 96.94%. The fully adaptive Swin model also reduces inference time from 16.51 ms to 14.05 ms relative to fixed Hebbian Swin. On CIFAR-FS, adaptive variants improve performance across all three backbones, and the multi-shot evaluation shows that these gains remain useful as the number of support examples increases. These results show that adaptive plasticity and adaptive memory activation can improve few-shot Transformer representations beyond fixed Hebbian behavior.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 23 references that are in the map. First posted on arXiv 23 Jun 2026.
Builds on
21 of 23 references.
References · 21
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
- 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
- 2022Mixture-of-Experts with Expert Choice Routingcited by 623
- 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 502
9 more
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
- 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 189
- 2016Using Fast Weights to Attend to the Recent Pastcited by 170
- 2015Conditional Computation in Neural Networks for faster modelscited by 167
- 2017Adaptive Neural Networks for Efficient Inferencecited by 163
- 2017Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learningcited by 126
- 2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 84
- 2018Metalearning with Hebbian Fast Weightscited by 15
- 2026Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognitioncited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.