paper-with-me

홈 › Papers

Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation

2024-05-23 · Daniel Kienzle, Marco Kantonis, Robin Schön, Rainer Lienhart

Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number of tokens through token merging, which has exhibited remarkable enhancements in inference speed, training efficiency, and memory utilization for image classification tasks. In this paper, we explore various token merging strategies within the framework of the Segformer architecture and perform experiments on multiple semantic segmentation and human pose estimation datasets. Notably, without model re-training, we, for example, achieve an inference acceleration of 61% on the Cityscapes dataset while maintaining the mIoU performance. Consequently, this paper facilitates the deployment of transformer-based architectures on resource-constrained devices and in real-time applications.

📄 PDF Abstract BibTeX arXiv:2405.14467

Code (2)

KieDani/SegformerPlusPlus 공식 구현 pytorch
yangyucheng000/University/tree/main/model-3/segformer mindspore

Tasks

image-classificationImage ClassificationPose EstimationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Mix-FFN Mix-FFN is a feedforward layer used in the SegFormer architecture.…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
SegFormer SegFormer is a Transformer-based framework for semantic segmentation that unifies Transformers with lightweight…

Similar Papers 제목 키워드 기반

DA-SegFormer: Damage-Aware Semantic Segmentation for Fine-Grained Disaster Assessment

2026-05-11 · Kevin Zhu, William Tang, Raphael Hay Tene, Zesheng Liu 외 arxiv

Rapid and accurate damage assessment following natural disasters is critical for effective emergency response. However, identifying fine-grained damage levels (e.g., distinguishing minor from major roof damage) in UAV im…

Semantic Segmentation

Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images using SegFormer

2024-10-01 · Vlatko Spasev, Ivica Dimitrovski, Ivan Chorbev, Ivan Kitanovski

The escalating use of Unmanned Aerial Vehicles (UAVs) as remote sensing platforms has garnered considerable attention, proving invaluable for ground object recognition. While satellite remote sensing images face limitati…

Object RecognitionSegmentationSemantic Segmentation

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

2021-05-31 · NeurIPS 2021 12 · Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar 외

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. SegFormer has two appealing features: 1) SegFormer …

2D Semantic SegmentationC++ codeCrack SegmentationDecoder+2

Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers

2021-11-24 · John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao 외

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, whic…

Computational EfficiencyOperator learningRepresentation Learning

Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators

2021-09-29 · ICLR 2022 4 · John Guibas, Morteza Mardani, Zongyi Li, Andrew Tao 외

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, whic…

Computational EfficiencyOperator learningRepresentation Learning