Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization

Unsupervised localization and segmentation are long-standing computer vision challenges that involve decom-posing an image into semantically meaningful segments without any labeled data. These tasks are particularly interesting in an unsupervised setting due to the difficulty and cost of obtaining d...

詳細記述

書誌詳細
主要な著者: Melas-Kyriazi, L, Rupprecht, C, Laina, I, Vedaldi, A
フォーマット: Conference item
言語:English
出版事項: IEEE 2022

類似資料