Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 482

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.

Neighborhood Attention Transformer

Open access
Hassani, Ali, Walton, Steven, Li, Jiachen, Li, Shen, Shi, Humphrey · 2023 · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

We present Neighborhood Attention (NA), the first efficient and scalable sliding window attention mechanism for vision. NA is a pixel-wise operation, localizing self attention (SA) to the nearest neighboring pixels, and therefore enjoys a linear time and space complexity compared to the quadratic complexity of SA. The sliding window pattern allows NA's receptive field to grow without needing extra pixel shifts, and preserves translational equivariance, unlike Swin Transformer's Window Self Attention (WSA). We develop NATTEN (Neighborhood Attention Extension), a Python package with efficient C++ and CUDA kernels, which allows NA to run up to 40% faster than Swin's WSA while using up to 25% less memory. We further present Neighborhood Attention Transformer (NAT), a new hierarchical transformer design based on NA that boosts image classification and downstream vision performance. Experimental results on NAT are competitive; NAT-Tiny reaches 83.2% top-1 accuracy on ImageNet, 51.4% mAP on MSCOCO and 48.4% mIoU on ADE20K, which is 1.9% ImageNet accuracy, 1.0% COCO mAP, and 2.6% ADE20K mIoU improvement over a Swin model with similar size. To support more research based on sliding window attention, we open source our project and release our checkpoints.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52729.2023.00599

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 8

  1. dosovitskiy, 0, An image is worth 16×16 words: Transformers for image recognition at scale, International Conference on Learning Representations (ICLR)
  2. goodfellow, 2016, Deep Learning
  3. vaswani, 0, Attention is all you need, Advances in Neural IInformation Processing Systems
  4. wightman, 2019, pytorch-image-models
  5. radford, 2019, Language Models are Unsuper-vised Multitask Learners
  6. radford, 2018, Improving language understanding by generative pre-training
  7. touvron, 2021, Training data-efficient image transformers & distillation through attention, International Conference on Machine Learning (ICML)
  8. 2020, MMSegmentation Contributors MMSegmentation Openmmlab semantic segmentation toolbox and benchmark

Cited by

See all 482

Metadata

Authors
Hassani, A., Walton, S., Li, J., Li, S., & Shi, H.
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
6185-6194
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4386075553
Cited by
482
References
39
FWCI
54.01
Type
conference paper
Language
en
Open access
green
Funders
Intelligence Advanced Research Projects Activity (IARPA) (2022-21102100004)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.