# Learned Queries for Efficient Local Attention

arXiv: https://arxiv.org/abs/2112.11435 · HTML: https://mlsanity.com/paper/2112.11435/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 91 references that are in the map.
- First posted on arXiv 21 Dec 2021.

## Builds on (most cited first, 30 of 76)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)

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

- [InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion](https://mlsanity.com/paper/2308.16905/) (2023)
- [Fast Video Generation with Sliding Tile Attention](https://mlsanity.com/paper/2502.04507/) (2025)
- [RMT: Retentive Networks Meet Vision Transformers](https://mlsanity.com/paper/2309.11523/) (2023)
- [Single Motion Diffusion](https://mlsanity.com/paper/2302.05905/) (2023)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention](https://mlsanity.com/paper/2304.04237/) (2023)
- [Vision Transformers with Mixed-Resolution Tokenization](https://mlsanity.com/paper/2304.00287/) (2023)
- [Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference](https://mlsanity.com/paper/2211.10526/) (2022)
- [Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers](https://mlsanity.com/paper/2403.10030/) (2024)
- [Lightweight Vision Transformer with Bidirectional Interaction](https://mlsanity.com/paper/2306.00396/) (2023)
- [DAT++: Spatially Dynamic Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2309.01430/) (2023)
- [ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer](https://mlsanity.com/paper/2306.06446/) (2023)
- [Iterative Patch Selection for High-Resolution Image Recognition](https://mlsanity.com/paper/2210.13007/) (2022)
- [When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models](https://mlsanity.com/paper/2406.07368/) (2024)
- [MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer](https://mlsanity.com/paper/2504.08959/) (2025)
- [Vision Transformer with Sparse Scan Prior](https://mlsanity.com/paper/2405.13335/) (2024)
- [Rethinking Local Perception in Lightweight Vision Transformer](https://mlsanity.com/paper/2303.17803/) (2023)
- [DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction](https://mlsanity.com/paper/2310.07438/) (2023)
- [A Manifold Representation of the Key in Vision Transformers](https://mlsanity.com/paper/2402.00534/) (2024)
- [Towards Practical Single-shot Motion Synthesis](https://mlsanity.com/paper/2406.01136/) (2024)
- [A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma](https://mlsanity.com/paper/2502.03772/) (2025)
- [Controllable Single-shot Animation Blending with Temporal Conditioning](https://mlsanity.com/paper/2508.18525/) (2025)
- [Token Transformer: Can class token help window-based transformer build better long-range interactions?](https://mlsanity.com/paper/2211.06083/) (2022)
- [Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work](https://mlsanity.com/paper/2306.01929/) (2023)
- [Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers](https://mlsanity.com/paper/2507.12125/) (2025)
- [Through the PRISm: Importance-Aware Scene Graphs for Image Retrieval](https://mlsanity.com/paper/2512.18407/) (2025)
- [Advancing Vision Transformer with Enhanced Spatial Priors](https://mlsanity.com/paper/2604.18549/) (2026)

## Abstract (arXiv)

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data. Nonetheless, an integral part of any transformer architecture, the self-attention mechanism, suffers from high latency and inefficient memory utilization, making it less suitable for high-resolution input images. To alleviate these shortcomings, hierarchical vision models locally employ self-attention on non-interleaving windows. This relaxation reduces the complexity to be linear in the input size; however, it limits the cross-window interaction, hurting the model performance. In this paper, we propose a new shift-invariant local attention layer, called query and attend (QnA), that aggregates the input locally in an overlapping manner, much like convolutions. The key idea behind QnA is to introduce learned queries, which allow fast and efficient implementation. We verify the effectiveness of our layer by incorporating it into a hierarchical vision transformer model. We show improvements in speed and memory complexity while achieving comparable accuracy with state-of-the-art models. Finally, our layer scales especially well with window size, requiring up-to x10 less memory while being up-to x5 faster than existing methods. The code is publicly available at urlhttps://github.com/moabarar/qna.