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...
Príomhchruthaitheoirí: | Melas-Kyriazi, L, Rupprecht, C, Laina, I, Vedaldi, A |
---|---|
Formáid: | Conference item |
Teanga: | English |
Foilsithe / Cruthaithe: |
IEEE
2022
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Finding an unsupervised image segmenter in each of your deep generative models
de réir: Melas-Kyriazi, L, et al.
Foilsithe / Cruthaithe: (2021) -
RealFusion: 360 reconstruction of any object from a single image
de réir: Melas-Kyriazi, L, et al.
Foilsithe / Cruthaithe: (2023) -
Unsupervised multi-object segmentation by predicting probable motion patterns
de réir: Karazija, L, et al.
Foilsithe / Cruthaithe: (2022) -
Guess what moves: unsupervised video and image segmentation by anticipating motion
de réir: Choudhury, S, et al.
Foilsithe / Cruthaithe: (2022) -
Unsupervised part discovery from contrastive reconstruction
de réir: Choudhury, S, et al.
Foilsithe / Cruthaithe: (2021)