# PARN: Position-Aware Relation Networks for Few-Shot Learning

arXiv: https://arxiv.org/abs/1909.04332 · HTML: https://mlsanity.com/paper/1909.04332/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2019.

## Built on by (most cited first, 27 of 27)

- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment](https://mlsanity.com/paper/2210.01439/) (2022)
- [Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning](https://mlsanity.com/paper/2203.09064/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification](https://mlsanity.com/paper/2208.12398/) (2022)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation](https://mlsanity.com/paper/2102.10935/) (2021)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2207.00784/) (2022)
- [Revisiting Local Descriptor for Improved Few-Shot Classification](https://mlsanity.com/paper/2103.16009/) (2021)
- [tSF: Transformer-based Semantic Filter for Few-Shot Learning](https://mlsanity.com/paper/2211.00868/) (2022)
- [Progressive Co-Attention Network for Fine-grained Visual Classification](https://mlsanity.com/paper/2101.08527/) (2021)
- [Local Propagation for Few-Shot Learning](https://mlsanity.com/paper/2101.01480/) (2021)
- [Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective](https://mlsanity.com/paper/2211.00890/) (2022)
- [Enabling the Network to Surf the Internet](https://mlsanity.com/paper/2102.12205/) (2021)
- [Towards Generative Class Prompt Learning for Fine-grained Visual Recognition](https://mlsanity.com/paper/2409.01835/) (2024)
- [BaseTransformers: Attention over base data-points for One Shot Learning](https://mlsanity.com/paper/2210.02476/) (2022)
- [TLRM: Task-level Relation Module for GNN-based Few-Shot Learning](https://mlsanity.com/paper/2101.09840/) (2021)
- [Few-shot Learning with Global Relatedness Decoupled-Distillation](https://mlsanity.com/paper/2107.05583/) (2021)
- [A Relational Model for One-Shot Classification](https://mlsanity.com/paper/2111.04313/) (2021)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2506.20263/) (2025)
- [CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective](https://mlsanity.com/paper/2512.21617/) (2025)

## Abstract (arXiv)

Few-shot learning presents a challenge that a classifier must quickly adapt to new classes that do not appear in the training set, given only a few labeled examples of each new class. This paper proposes a position-aware relation network (PARN) to learn a more flexible and robust metric ability for few-shot learning. Relation networks (RNs), a kind of architectures for relational reasoning, can acquire a deep metric ability for images by just being designed as a simple convolutional neural network (CNN) [23]. However, due to the inherent local connectivity of CNN, the CNN-based relation network (RN) can be sensitive to the spatial position relationship of semantic objects in two compared images. To address this problem, we introduce a deformable feature extractor (DFE) to extract more efficient features, and design a dual correlation attention mechanism (DCA) to deal with its inherent local connectivity. Successfully, our proposed approach extents the potential of RN to be position-aware of semantic objects by introducing only a small number of parameters. We evaluate our approach on two major benchmark datasets, i.e., Omniglot and Mini-Imagenet, and on both of the datasets our approach achieves state-of-the-art performance with the setting of using a shallow feature extraction network. It's worth noting that our 5-way 1-shot result on Omniglot even outperforms the previous 5-way 5-shot results.