Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 208

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Scale-Aware Modulation Meet Transformer

Open access
Lin, Weifeng, Wu, Ziheng, Chen, Jiayu, Huang, Jun, Jin, Lianwen·2023·2023 IEEE/CVF International Conference on Computer Vision (ICCV)

Abstract

This paper presents a new vision Transformer, Scale-Aware Modulation Transformer (SMT), that can handle various downstream tasks efficiently by combining the convolutional network and vision Transformer. The proposed Scale-Aware Modulation (SAM) in the SMT includes two primary novel designs. Firstly, we introduce the Multi-Head Mixed Convolution (MHMC) module, which can capture multi-scale features and expand the receptive field. Secondly, we propose the Scale-Aware Aggregation (SAA) module, which is lightweight but effective, enabling information fusion across different heads. By leveraging these two modules, convolutional modulation is further enhanced. Furthermore, in contrast to prior works that utilized modulations throughout all stages to build an attention-free network, we propose an Evolutionary Hybrid Network (EHN), which can effectively simulate the shift from capturing local to global dependencies as the network becomes deeper, resulting in superior performance. Extensive experiments demonstrate that SMT significantly outperforms existing state-of-the-art models across a wide range of visual tasks. Specifically, SMT with 11.5M / 2.4GFLOPs and 32M / 7.7GFLOPs can achieve 82.2% and 84.3% top-1 accuracy on ImageNet-1K, respectively. After pretrained on ImageNet-22K in 2242resolution, it attains 87.1% and 88.1% top-1 accuracy when finetuned with resolution 2242and 3842, respectively. For object detection with Mask R-CNN, the SMT base trained with 1× and 3× schedule outperforms the Swin Transformer counterpart by 4.2 and 1.3 mAP on COCO, respectively. For semantic segmentation with UPerNet, the SMT base test at single- and multi-scale surpasses Swin by 2.0 and 1.1 mIoU respectively on the ADE20K. Our code is available at https://github.com/AFeng-x/SMT.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/iccv51070.2023.00553

Cites

31 of 31 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Show all 31 references

Cited by

See all 208

Metadata

Authors
Lin, W., Wu, Z., Chen, J., Huang, J., & Jin, L.
Venue
2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2023-10-01
Pages
5992-6003
OpenAlex
W4390872693
Cited by
208
References
31
FWCI
23.65
Type
conference paper
Language
en
Open access
green

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Scale-Aware Modulation Meet Transformer. https://app.cochat.ai/papers/10.1109/iccv51070.2023.00553
The paper
Lin, W., Wu, Z., Chen, J., Huang, J., & Jin, L. (2023). Scale-Aware Modulation Meet Transformer. 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv51070.2023.00553

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.