Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Decoupling Zero-Shot Semantic Segmentation

Ding, J., Xue, N., Xia, G.-S., & Dai, D. (2022). Decoupling Zero-Shot Semantic Segmentation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 11573-11582). Piscataway, NJ: IEEE. doi:10.1109/CVPR52688.2022.01129.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-000A-16BD-9 Versions-Permalink: https://hdl.handle.net/21.11116/0000-000C-1272-F
Genre: Konferenzbeitrag

Dateien

einblenden: Dateien
ausblenden: Dateien
:
arXiv:2112.07910.pdf (Preprint), 14MB
 
Datei-Permalink:
-
Name:
arXiv:2112.07910.pdf
Beschreibung:
File downloaded from arXiv at 2022-03-09 14:50
OA-Status:
Sichtbarkeit:
Privat
MIME-Typ / Prüfsumme:
application/pdf
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
http://arxiv.org/licenses/nonexclusive-distrib/1.0/
:
Ding_Decoupling_Zero-Shot_Semantic_Segmentation_CVPR_2022_paper.pdf (Preprint), 5MB
Öffnen   Speichern
Datei-Permalink:
https://hdl.handle.net/21.11116/0000-000C-1271-0
Name:
Ding_Decoupling_Zero-Shot_Semantic_Segmentation_CVPR_2022_paper.pdf
Beschreibung:
-
OA-Status:
Keine Angabe
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Öffnen
Copyright Datum:
-
Copyright Info:
These CVPR 2021 papers are the Open Access versions, provided by the Computer Vision Foundation. Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Lizenz:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Ding, Jian1, Autor
Xue, Nan1, Autor
Xia, Gui-Song1, Autor
Dai, Dengxin2, Autor           
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Zusammenfassung: Zero-shot semantic segmentation (ZS3) aims to segment the novel categories
that have not been seen in the training. Existing works formulate ZS3 as a
pixel-level zero-shot classification problem, and transfer semantic knowledge
from seen classes to unseen ones with the help of language models pre-trained
only with texts. While simple, the pixel-level ZS3 formulation shows the
limited capability to integrate vision-language models that are often
pre-trained with image-text pairs and currently demonstrate great potential for
vision tasks. Inspired by the observation that humans often perform
segment-level semantic labeling, we propose to decouple the ZS3 into two
sub-tasks: 1) a class-agnostic grouping task to group the pixels into segments.
2) a zero-shot classification task on segments. The former sub-task does not
involve category information and can be directly transferred to group pixels
for unseen classes. The latter subtask performs at segment-level and provides a
natural way to leverage large-scale vision-language models pre-trained with
image-text pairs (e.g. CLIP) for ZS3. Based on the decoupling formulation, we
propose a simple and effective zero-shot semantic segmentation model, called
ZegFormer, which outperforms the previous methods on ZS3 standard benchmarks by
large margins, e.g., 35 points on the PASCAL VOC and 3 points on the COCO-Stuff
in terms of mIoU for unseen classes. Code will be released at
https://github.com/dingjiansw101/ZegFormer.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2021-12-1520222022
 Publikationsstatus: Online veröffentlicht
 Seiten: 14 pages, 8 figures
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: Ding_CVPR2022
DOI: 10.1109/CVPR52688.2022.01129
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition
Veranstaltungsort: New Orleans, LA, USA
Start-/Enddatum: 2022-06-19 - 2022-06-24

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: IEEE/CVF Conference on Computer Vision and Pattern Recognition
  Kurztitel : CVPR 2022
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 11573 - 11582 Identifikator: ISBN: 978-1-6654-6946-3