A Sequence-to-sequence prediction approach for semantic segmentation

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

A Sequence-to-sequence prediction approach for semantic segmentation

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Semantic segmentation is a key step in the design of semantic segmentation models.

Specifically, we deploy a puretransformer (ie.

Without convolution and resolution reduction) to encode an image as a sequence of patches.

With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed segmentation transformer (setr).

Extensive experiments show that setr achieves new state of the art on ade20k (50.28% miou), pascal context (55.83% miou) and competitive results on cityscapes.

Particularly, we achieve the first (44.42% miou) position in the highly competitive ade20k test server leaderboard.