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