# ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation

arXiv: https://arxiv.org/abs/2507.09299 · HTML: https://mlsanity.com/paper/2507.09299/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://mlsanity.com/paper/1812.01187/) (2018)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Edge-labeling Graph Neural Network for Few-shot Learning](https://mlsanity.com/paper/1905.01436/) (2019)
- [Laplacian Regularized Few-Shot Learning](https://mlsanity.com/paper/2006.15486/) (2020)
- [Rethinking Generalization in Few-Shot Classification](https://mlsanity.com/paper/2206.07267/) (2022)
- [Task Augmentation by Rotating for Meta-Learning](https://mlsanity.com/paper/2003.00804/) (2020)
- [Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning](https://mlsanity.com/paper/2110.09446/) (2021)
- [Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification](https://mlsanity.com/paper/2209.08527/) (2022)
- [Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning](https://mlsanity.com/paper/2107.13093/) (2021)
- [The Balanced-Pairwise-Affinities Feature Transform](https://mlsanity.com/paper/2407.01467/) (2024)

## Abstract (arXiv)

The remarkable representational power of Vision Transformers (ViTs) remains underutilized in few-shot image classification. In this work, we introduce ViT-ProtoNet, which integrates a ViT-Small backbone into the Prototypical Network framework. By averaging class conditional token embeddings from a handful of support examples, ViT-ProtoNet constructs robust prototypes that generalize to novel categories under 5-shot settings. We conduct an extensive empirical evaluation on four standard benchmarks: Mini-ImageNet, FC100, CUB-200, and CIFAR-FS, including overlapped support variants to assess robustness. Across all splits, ViT-ProtoNet consistently outperforms CNN-based prototypical counterparts, achieving up to a 3.2% improvement in 5-shot accuracy and demonstrating superior feature separability in latent space. Furthermore, it outperforms or is competitive with transformer-based competitors using a more lightweight backbone. Comprehensive ablations examine the impact of transformer depth, patch size, and fine-tuning strategy. To foster reproducibility, we release code and pretrained weights. Our results establish ViT-ProtoNet as a powerful, flexible approach for few-shot classification and set a new baseline for transformer-based meta-learners.