STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Study

STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Insight Miner 2022. 7. 29. 16:52

MIT CSAIL에서 발표한 Unsupervised Semantic Segmentation 연구

GitHub - mhamilton723/STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Unsupervised Semantic Segmentation by Distilling Feature Correspondences - GitHub - mhamilton723/STEGO: Unsupervised Semantic Segmentation by Distilling Feature Correspondences

github.com

https://arxiv.org/abs/2203.08414

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both semantically meaning

arxiv.org