TUdatalib : Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals

Zur Kurzanzeige

dc.contributor.author	Hahn, Oliver
dc.contributor.author	Araslanov, Nikita
dc.contributor.author	Schaub-Meyer, Simone
dc.contributor.author	Roth, Stefan
dc.date.accessioned	2025-04-03T11:44:00Z
dc.date.available	2025-04-03T11:44:00Z
dc.date.issued	2024-09
dc.identifier.uri	https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4530
dc.description	Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global semantic categories within an image corpus without any form of annotation. Building upon recent advances in self-supervised representation learning, we focus on how to leverage these large pre-trained models for the downstream task of unsupervised segmentation. We present PriMaPs – Principal Mask Proposals – decomposing images into semantically meaningful masks based on their feature representation. This allows us to realize unsupervised semantic segmentation by fitting class prototypes to PriMaPs with a stochastic expectation-maximization algorithm, PriMaPs-EM. Despite its conceptual simplicity, PriMaPs-EM leads to competitive results across various pre-trained backbone models, including DINO and DINOv2, and across different datasets, such as Cityscapes, COCO-Stuff, and Potsdam-3. Importantly, PriMaPs-EM is able to boost results when applied orthogonally to current state-of-the-art unsupervised semantic segmentation pipelines.	de_DE
dc.language.iso	en	de_DE
dc.relation	IsDescribedBy;arXiv;https://arxiv.org/abs/2404.16818
dc.relation	IsDescribedBy;URL;https://openreview.net/forum?id=UawaTQzfwy
dc.relation	IsDescribedBy;URL;https://github.com/visinf/primaps
dc.rights	Apache License 2.0
dc.rights.uri	https://www.apache.org/licenses/LICENSE-2.0
dc.subject	Semantic Segmentation	de_DE
dc.subject	Self-Supervised	de_DE
dc.subject	Unsupervised Semantic Segmentation	de_DE
dc.subject	Deep Learning	de_DE
dc.subject.classification	4.43-04 Künstliche Intelligenz und Maschinelle Lernverfahren	de_DE
dc.subject.ddc	004
dc.title	Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals	de_DE
dc.type	Software	de_DE
tud.project	EC/H2020 \| 866008 \| RED	de_DE
tud.project	HMWK \| 500/10.001-(00111) \| 3AI - TP Roth	de_DE
tud.project	HMWK \| 500/10.001-(00012) \| TAM - TP Roth	de_DE
tud.project	HMWK \| 500/10.001-(00111) \| 3AI-NWG Schaub-Meyer	de_DE
tud.unit	TUDa

Dateien zu dieser Ressource

Name:: primaps-code.zip
Größe:: 3.617MB
Format:: application/zip

Anzahl der Dateien

Name:: primaps_checkpoints.zip
Größe:: 2.501GB
Format:: application/zip

Anzahl der Dateien

Der Datensatz erscheint in:

Segmentation [8]

Zur Kurzanzeige

Solange nicht anders angezeigt, wird die Lizenz wie folgt beschrieben: Apache License 2.0