Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 456

The DOI matches its Crossref record; 84 of the 84 references it cites were found in a registry or an index.

GroupViT: Semantic Segmentation Emerges from Text Supervision

Open access
Xu, Jiarui, De Mello, Shalini, Liu, Sifei, Byeon, Wonmin, Breuel, Thomas, Kautz, Jan, Wang, Xiaolong·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens implicitly via top-down supervision from pixel-level recognition labels. Instead, in this paper, we propose to bring back the grouping mechanism into deep networks, which allows semantic segments to emerge automatically with only text supervision. We propose a hierarchical Grouping Vision Transformer (GroupViT), which goes beyond the regular grid structure representation and learns to group image regions into progressively larger arbitrary-shaped segments. We train GroupViT jointly with a text encoder on a large-scale image-text dataset via contrastive losses. With only text supervision and without any pixel-level annotations, GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner, i.e., without any further fine-tuning. It achieves a zero-shot accuracy of 52.3% mIoU on the PASCAL VOC 2012 and 22.4% mIoU on PASCAL Context datasets, and performs competitively to state-of-the-art transfer-learning methods requiring greater levels of supervision. We open-source our code at https://github.com/NVlabs/GroupViT.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52688.2022.01760

Cites

84 of 84 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 15

  1. Bucher, 2019, Zero-shot semantic segmentation
  2. Casanova, 2020, Reinforced active learning for image segmentation
  3. Dong, 2018, Few-shot semantic segmentation with prototype learning
  4. Dosovitskiy, 2021, An image is worth 16x16 words: Transformers for image recognition at scale
  5. Gan, 2020, Large-scale adversarial training for vision-and-language representation learning
  6. Kingma, 2015, Adam: A method for stochastic optimization
  7. Li, 2020, Consistent structural relation learning for zero-shot segmentation
  8. Locatello, 2020, Object-centric learning with slot attention
  9. Maddison, 2017, The concrete distribution: A continuous relaxation of discrete random variables
  10. Ryoo, 2021, Tokenlearner: What can 8 learned tokens do for images and videos?
  11. Touvron, 2021, Training data-efficient image transformers & distillation through attention
  12. 10.1109/ICCV.2003.1238309 · doi:10.1109/iccv.2003.1238309
  13. Vaswani, 2017, Attention is all you need
  14. Xie, 2021, Segformer: Simple and efficient design for semantic segmentation with transformers
  15. Zhang, 2021, Multi-scale vision long-former: A new vision transformer for high-resolution image encoding

Cited by

See all 456

Metadata

Authors
Xu, J., De Mello, S., Liu, S., Byeon, W., Breuel, T., Kautz, J., & Wang, X.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
18113-18123
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4312980231
Cited by
456
References
84
FWCI
37.86
Type
conference paper
Language
en
Open access
green
Funders
NSF (CCF-2112665 (TILOS))

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.