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

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...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors:	Melas-Kyriazi, L, Rupprecht, C, Laina, I, Vedaldi, A
Format:	Conference item
Sprog:	English
Udgivet:	IEEE 2022

Lignende værker

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

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

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

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

Unsupervised part discovery from contrastive reconstruction
af: Choudhury, S, et al.
Udgivet: (2021)

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

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

Diffusion models for open-vocabulary segmentation
af: Karazija, L, et al.
Udgivet: (2024)

Learning segmentation from point trajectories
af: Karazija, L, et al.
Udgivet: (2025)

Diffusion models for open-vocabulary segmentation
af: Karazija, L, et al.
Udgivet: (2023)

AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong
af: Jannis Blüml, et al.
Udgivet: (2023-05-01)

The Surprising Effectiveness of Deep Orthogonal Procrustes Alignment in Unsupervised Domain Adaptation
af: Kowshik Thopalli, et al.
Udgivet: (2023-01-01)

Large-scale unsupervised semantic segmentation
af: Gao, S, et al.
Udgivet: (2022)

Latent space unsupervised semantic segmentation
af: Knut J. Strommen, et al.
Udgivet: (2023-04-01)

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

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

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

Invariant information clustering for unsupervised image classification and segmentation
af: Ji, X, et al.
Udgivet: (2020)

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

SmooSeg: smoothness prior for unsupervised semantic segmentation
af: Lan, Mengcheng, et al.
Udgivet: (2024)

Unsupervised Domain Adaptation in Semantic Segmentation: A Review
af: Marco Toldo, et al.
Udgivet: (2020-06-01)

Pylon model for semantic segmentation
af: Lempitsky, V, et al.
Udgivet: (2012)

Adversarial cross-modal unsupervised domain adaptation in semantic segmentation
af: Shi, Mengqi
Udgivet: (2022)

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
af: Jose L. Gómez, et al.
Udgivet: (2023-01-01)

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation with Transformer
af: Weitao Li, et al.
Udgivet: (2022-10-01)

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

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity
af: Meilin Li, et al.
Udgivet: (2024-01-01)

Unsupervised TOF Image Segmentation through Spectral Clustering and Region Merging
af: Luciano Lorenti, et al.
Udgivet: (2018-10-01)

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

Moving SLAM: fully unsupervised deep learning in non-rigid scenes
af: Xu, D, et al.
Udgivet: (2021)

Voxel-based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs Deep Learning Methods
af: Florent Poux, et al.
Udgivet: (2019-05-01)

Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
af: Manuel Schwonberg, et al.
Udgivet: (2023-01-01)

Semantic surprise predicts the N400 brain potential
af: Alma Lindborg, et al.
Udgivet: (2023-03-01)

Unsupervised Deep Learning for Bayesian Brain MRI Segmentation
af: Dalca, Adrian Vasile, et al.
Udgivet: (2021)

Understanding Unsupervised Deep Learning for Text Line Segmentation
af: Ahmad Droby, et al.
Udgivet: (2022-09-01)

DIC: Deep Image Clustering for Unsupervised Image Segmentation
af: Lei Zhou, et al.
Udgivet: (2020-01-01)

Log-Based Fault Localization with Unsupervised Log Segmentation
af: Wojciech Dobrowolski, et al.
Udgivet: (2024-09-01)

An unsupervised semantic segmentation method that combines the ImSE-Net model with SLICm superpixel optimization
af: Zenan Yang, et al.
Udgivet: (2024-12-01)

Deep Semantic-Preserving Reconstruction Hashing for Unsupervised Cross-Modal Retrieval
af: Shuli Cheng, et al.
Udgivet: (2020-11-01)

BiFDANet: Unsupervised Bidirectional Domain Adaptation for Semantic Segmentation of Remote Sensing Images
af: Yuxiang Cai, et al.
Udgivet: (2022-01-01)