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

Source: [Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation](<https://www.sota2.com/research/paper/68fa73451e209131cea5b6fc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:46:17.278Z

Authors: Daniel Kienzle, Marco Kantonis, Robin Sch\\"on, Rainer Lienhart

Published: 2024-05-23T11:54:27.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.14467>)

[PDF](<https://arxiv.org/pdf/2405.14467.pdf>)