MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation Article Swipe

MAKE IMPACT

Jing Xu , Wentao Shi , Pan Gao , Zhengwei Wang , Qizhu Li · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2211.13928

In recent works on semantic segmentation, there has been a significant focus on designing and integrating transformer-based encoders. However, less attention has been given to transformer-based decoders. We emphasize that the decoder stage is equally vital as the encoder in achieving superior segmentation performance. It disentangles and refines high-level cues, enabling precise object boundary delineation at the pixel level. In this paper, we introduce a novel transformer-based decoder called MUSTER, which seamlessly integrates with hierarchical encoders and consistently delivers high-quality segmentation results, regardless of the encoder architecture. Furthermore, we present a variant of MUSTER that reduces FLOPS while maintaining performance. MUSTER incorporates carefully designed multi-head skip attention (MSKA) units and introduces innovative upsampling operations. The MSKA units enable the fusion of multi-scale features from the encoder and decoder, facilitating comprehensive information integration. The upsampling operation leverages encoder features to enhance object localization and surpasses traditional upsampling methods, improving mIoU (mean Intersection over Union) by 0.4% to 3.2%. On the challenging ADE20K dataset, our best model achieves a single-scale mIoU of 50.23 and a multi-scale mIoU of 51.88, which is on-par with the current state-of-the-art model. Remarkably, we achieve this while significantly reducing the number of FLOPs by 61.3%. Our source code and models are publicly available at: https://github.com/shiwt03/MUSTER.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2211.13928

PDF

https://arxiv.org/pdf/2211.13928

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4310282807

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4310282807

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2211.13928

Digital Object Identifier

Title

MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-11-25

Full publication date if available

Authors

Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li

List of authors in order

Landing page

https://arxiv.org/abs/2211.13928

Publisher landing page

PDF URL

https://arxiv.org/pdf/2211.13928

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2211.13928

Direct OA link when available

Concepts

Upsampling, Computer science, Segmentation, Encoder, Transformer, Artificial intelligence, Computer vision, Pixel, Pattern recognition (psychology), Image (mathematics), Engineering, Voltage, Operating system, Electrical engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2024: 1, 2023: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload