# PAUMER: Patch Pausing Transformer for Semantic Segmentation

Source: [PAUMER: Patch Pausing Transformer for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa71121e209131cea4f173>)

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

Data updated: 2025-10-26T01:57:41.618Z

Authors: Evann Courdier, Prabhu Teja Sivaprasad, Fran\\c{c}ois Fleuret

Published: 2023-11-01T15:32:11.000Z

## Abstract

We study the problem of improving the efficiency of segmentation transformers by using disparate amounts of computation for different parts of the image. Our method, PAUMER, accomplishes this by pausing computation for patches that are deemed to not need any more computation before the final decoder. We use the entropy of predictions computed from intermediate activations as the pausing criterion, and find this aligns well with semantics of the image. Our method has a unique advantage that a single network trained with the proposed strategy can be effortlessly adapted at inference to various run-time requirements by modulating its pausing parameters. On two standard segmentation datasets, Cityscapes and ADE20K, we show that our method operates with about a $50\\%$ higher throughput with an mIoU drop of about $0.65\\%$ and $4.6\\%$ respectively.

## 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/2311.00586>)

[PDF](<https://arxiv.org/pdf/2311.00586.pdf>)