# Semantic Segmentation by Early Region Proxy

Source: [Semantic Segmentation by Early Region Proxy](<https://www.sota2.com/research/paper/68fa6c1b1e209131cea323f2>)

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

Data updated: 2026-01-04T05:12:13.217Z

Authors: Yifan Zhang, Bo Pang, Cewu Lu

Published: 2022-03-26T10:48:32.000Z

## Abstract

Typical vision backbones manipulate structured features. As a compromise, semantic segmentation has long been modeled as per-point prediction on dense regular grids. In this work, we present a novel and efficient modeling that starts from interpreting the image as a tessellation of learnable regions, each of which has flexible geometrics and carries homogeneous semantics. To model region-wise context, we exploit Transformer to encode regions in a sequence-to-sequence manner by applying multi-layer self-attention on the region embeddings, which serve as proxies of specific regions. Semantic segmentation is now carried out as per-region prediction on top of the encoded region embeddings using a single linear classifier, where a decoder is no longer needed. The proposed RegProxy model discards the common Cartesian feature layout and operates purely at region level. Hence, it exhibits the most competitive performance-efficiency trade-off compared with the conventional dense prediction methods. For example, on ADE20K, the small-sized RegProxy-S/16 outperforms the best CNN model using 25% parameters and 4% computation, while the largest RegProxy-L/16 achieves 52.9mIoU which outperforms the state-of-the-art by 2.1% with fewer resources. Codes and models are available at https://github.com/YiF-Zhang/RegionProxy.

## 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.

- [Semantic Segmentation on PASCAL Context (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-val.md>): Semantic segmentation; PASCAL Context (val); mIoU: 58.4.

- [Semantic Segmentation on ADE20K (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-ade20k-val.md>): Semantic segmentation; ADE20K (val); mIoU: 52.9.

- [Semantic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-val.md>): Semantic segmentation; Cityscapes (val); mIoU: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.14043>)

[PDF](<https://arxiv.org/pdf/2203.14043.pdf>)

[Implementation](<https://github.com/YiF-Zhang/RegionProxy>)