# A Unified Efficient Pyramid Transformer for Semantic Segmentation

Source: [A Unified Efficient Pyramid Transformer for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa6a711e209131cea2818a>)

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

Data updated: 2025-10-25T23:24:37.002Z

Authors: Fangrui Zhu, Yi Zhu, Li Zhang, Chongruo Wu, Yanwei Fu, Mu Li

Published: 2021-07-29T17:47:32.000Z

## Abstract

Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less generalizable in open-world scenarios. In this work, we advocate a unified framework(UN-EPT) to segment objects by considering both context information and boundary artifacts. We first adapt a sparse sampling strategy to incorporate the transformer-based attention mechanism for efficient context modeling. In addition, a separate spatial branch is introduced to capture image details for boundary refinement. The whole model can be trained in an end-to-end manner. We demonstrate promising performance on three popular benchmarks for semantic segmentation with low memory footprint. Code will be released soon.

## 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/2107.14209>)

[PDF](<https://arxiv.org/pdf/2107.14209.pdf>)