TUdatalib : Dense Unsupervised Learning for Video Segmentation

Zur Kurzanzeige

dc.contributor.author	Araslanov, Nikita
dc.contributor.author	Schaub-Meyer, Simone
dc.contributor.author	Roth, Stefan
dc.date.accessioned	2023-08-04T09:52:41Z
dc.date.available	2021-12-22T11:09:23Z
dc.date.available	2023-08-04T09:52:41Z
dc.date.issued	2021-12
dc.identifier.uri	https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3365.2
dc.description	We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.	de_DE
dc.language.iso	en	de_DE
dc.relation	IsDescribedBy;arXiv;2111.06265
dc.rights	Apache License 2.0
dc.rights.uri	https://www.apache.org/licenses/LICENSE-2.0
dc.subject	self-supervised learning	de_DE
dc.subject	video object segmentation	de_DE
dc.subject	representation learning	de_DE
dc.subject.classification	409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung	de_DE
dc.subject.ddc	004
dc.title	Dense Unsupervised Learning for Video Segmentation	de_DE
dc.type	Software	de_DE
tud.project	EC/H2020 \| 866008 \| RED	de_DE
tud.project	HMWK \| III L6-519/03/05.001-(0016) \| emergenCity - TP Roth	de_DE
tud.unit	TUDa