Unsupervised part discovery from contrastive reconstruction

Unsupervised part discovery from contrastive reconstruction

Detalhes bibliográficos
Main Authors:	Choudhury, S, Laina, I, Rupprecht, C, Vedaldi, A
Formato:	Conference item
Idioma:	English
Publicado em:	NeurIPS Proceedings 2021

Registos relacionados

Unsupervised multi-object segmentation by predicting probable motion patterns
Por: Karazija, L, et al.
Publicado em: (2022)

Guess what moves: unsupervised video and image segmentation by anticipating motion
Por: Choudhury, S, et al.
Publicado em: (2022)

Finding an unsupervised image segmenter in each of your deep generative models
Por: Melas-Kyriazi, L, et al.
Publicado em: (2021)

Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization
Por: Melas-Kyriazi, L, et al.
Publicado em: (2022)

RealFusion: 360 reconstruction of any object from a single image
Por: Melas-Kyriazi, L, et al.
Publicado em: (2023)

The curious layperson: fine-grained image recognition without expert labels
Por: Choudhury, S, et al.
Publicado em: (2022)

Measuring the interpretability of unsupervised representations via quantized reversed probing
Por: Laina, I, et al.
Publicado em: (2021)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
Por: Wu, S, et al.
Publicado em: (2021)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
Por: Wu, S, et al.
Publicado em: (2020)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild (extended abstract)
Por: Wu, S, et al.
Publicado em: (2021)

Learning segmentation from point trajectories
Por: Karazija, L, et al.
Publicado em: (2025)

Unsupervised discovery of parts, structure, and dynamics
Por: Xu, Zhenjia, et al.
Publicado em: (2020)

Unsupervised discovery of nonlinear structure using contrastive backpropagation.
Por: Hinton, G, et al.
Publicado em: (2006)

Diffusion models for open-vocabulary segmentation
Por: Karazija, L, et al.
Publicado em: (2024)

Invisible stitch: generating smooth 3D scenes with depth inpainting
Por: Engstler, P, et al.
Publicado em: (2024)

Diffusion models for open-vocabulary segmentation
Por: Karazija, L, et al.
Publicado em: (2023)

Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Por: Bhalgat, Y, et al.
Publicado em: (2024)

IM-3D: iterative multiview diffusion and reconstruction for high-quality 3D generation
Por: Melas-Kyriazi, L, et al.
Publicado em: (2024)

Splatter image: ultra-fast single-view 3D reconstruction
Por: Szymanowicz, S, et al.
Publicado em: (2024)

Splatter image: ultra-fast single-view 3D reconstruction
Por: Szymanowicz, S, et al.
Publicado em: (2023)

Automatic discovery and optimization of parts for image classification
Por: Parizi, SN, et al.
Publicado em: (2015)

Unsupervised intuitive physics from visual observations
Por: Ehrhardt, S, et al.
Publicado em: (2019)

PC2: projection-conditioned point cloud diffusion for single-image 3D reconstruction
Por: Melas-Kyriazi, L, et al.
Publicado em: (2023)

Unsupervised Discovery of Biographical Structure from Text
Por: David Bamman, et al.
Publicado em: (2021-03-01)

DragAPart: learning a part-level motion prior for articulated objects
Por: Li, R, et al.
Publicado em: (2024)

DragAPart: learning a part-level motion prior for articulated objects
Por: Li, R, et al.
Publicado em: (2024)

Unsupervised Lexicon Discovery from Acoustic Input
Por: Chia-ying Lee, et al.
Publicado em: (2024-07-01)

Unsupervised Lexicon Discovery from Acoustic Input
Por: Lee, Chia-ying, et al.
Publicado em: (2015)

Kalman contrastive unsupervised representation learning
Por: Mohammad Mahdi Jahani Yekta
Publicado em: (2024-12-01)

Unsupervised Workflow Discovery in Provenance Graphs
Por: Yue, Kevin
Publicado em: (2022)

Learning to read by spelling: towards unsupervised text recognition
Por: Gupta, A, et al.
Publicado em: (2018)

Learning to read by spelling: towards unsupervised text recognition
Por: Gupta, A, et al.
Publicado em: (2020)

Unsupervised learning of landmarks by descriptor vector exchange
Por: Thewlis, J, et al.
Publicado em: (2020)

Unsupervised discovery of visual object class hierarchies
Por: Sivic, J, et al.
Publicado em: (2008)

Invariant information clustering for unsupervised image classification and segmentation
Por: Ji, X, et al.
Publicado em: (2020)

Modelling and unsupervised learning of symmetric deformable object categories
Por: Thewlis, J, et al.
Publicado em: (2018)

Unsupervised learning of object landmarks by factorized spatial embeddings
Por: Thewlis, J, et al.
Publicado em: (2017)

Viewset diffusion: (0-)image-conditioned 3D generative models from 2D data
Por: Szymanowicz, S, et al.
Publicado em: (2023)

Viewset Diffusion: (0-)image-conditioned 3D generative models from 2D data
Por: Szymanowicz, S, et al.
Publicado em: (2024)

Flash3D: feed-forward generalisable 3D scene reconstruction from a single image
Por: Szymanowicz, S, et al.
Publicado em: (2024)