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...
Autori principali: | Melas-Kyriazi, L, Rupprecht, C, Laina, I, Vedaldi, A |
---|---|
Natura: | Conference item |
Lingua: | English |
Pubblicazione: |
IEEE
2022
|
Documenti analoghi
Documenti analoghi
-
Finding an unsupervised image segmenter in each of your deep generative models
di: Melas-Kyriazi, L, et al.
Pubblicazione: (2021) -
RealFusion: 360 reconstruction of any object from a single image
di: Melas-Kyriazi, L, et al.
Pubblicazione: (2023) -
Unsupervised multi-object segmentation by predicting probable motion patterns
di: Karazija, L, et al.
Pubblicazione: (2022) -
Guess what moves: unsupervised video and image segmentation by anticipating motion
di: Choudhury, S, et al.
Pubblicazione: (2022) -
Unsupervised part discovery from contrastive reconstruction
di: Choudhury, S, et al.
Pubblicazione: (2021)