# SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning

arXiv: https://arxiv.org/abs/2303.09281 · HTML: https://mlsanity.com/paper/2303.09281/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Learning feed-forward one-shot learners](https://mlsanity.com/paper/1606.05233/) (2016)
- [Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning](https://mlsanity.com/paper/2102.03983/) (2021)
- [Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning](https://mlsanity.com/paper/1905.01102/) (2019)
- [Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning](https://mlsanity.com/paper/2103.01315/) (2021)
- [Pareto Self-Supervised Training for Few-Shot Learning](https://mlsanity.com/paper/2104.07841/) (2021)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning](https://mlsanity.com/paper/2001.03919/) (2020)
- [Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification](https://mlsanity.com/paper/2106.05517/) (2021)
- [tSF: Transformer-based Semantic Filter for Few-Shot Learning](https://mlsanity.com/paper/2211.00868/) (2022)
- [Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective](https://mlsanity.com/paper/2211.00890/) (2022)

## Built on by (most cited first, 4 of 4)

- [XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage](https://mlsanity.com/paper/2403.06768/) (2024)
- [KNN Transformer with Pyramid Prompts for Few-Shot Learning](https://mlsanity.com/paper/2410.10227/) (2024)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05135/) (2026)

## Abstract (arXiv)

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate discriminative representations via enhancing the mutually semantic similar regions of support and query pairs. However, it suffers from two problems: CNN structure produces inaccurate attention map based on local features, and mutually similar backgrounds cause distraction. To alleviate these problems, we design a novel SpatialFormer structure to generate more accurate attention regions based on global features. Different from the traditional Transformer modeling intrinsic instance-level similarity which causes accuracy degradation in FSL, our SpatialFormer explores the semantic-level similarity between pair inputs to boost the performance. Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction. Particularly, SFSA highlights the regions with same semantic information between pair features, and SFTA finds potential foreground object regions of novel feature that are similar to base categories. Extensive experiments show that our methods are effective and achieve new state-of-the-art results on few-shot classification benchmarks.