CoChat
Sign Up
Cited by 293Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningMultimodal Machine Learning Applications

Self-supervised model adaptation for multimodal semantic segmentation

Open access
Valada, Abhinav, Mohan, Rohit, Burgard, Wolfram·2020·International Journal of Computer Vision
DOI 10.1007/s11263-019-01188-y
Open this paper in CoChat — free accountOpen PDF

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 · 10.1007/s11263-019-01188-y

Cites

60 of 60 references verified0 citation errors · 0 not checkable

Statistics

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Roitberg et al. compared and analyzed seven decision-level fusion strategies for driver behavior understanding.

    “Roitberg et al. [47] compared and analyzed seven decision-level fusion strategies for driver behavior understanding, offering valuable insights for selecting appropriate fusion schemes.”

    From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [47]

    The Multimodal Fusion Ablation Studies (p. 34) and Fusion Stage and Reliance on Modalities (p. 35) compare configurations of this paper’s semantic-segmentation model, not seven decision-level strategies for driver behavior understanding. Searches for Roitberg and the seven-strategy claim found no passage in our copy addressing it. (LLM, conf=0.75)

    Experimental — accuracy not yet measured

  • A very common architectural choice is to adopt a multi-stream architecture for the encoder with a network branch processing each modality and additional network modules connecting the different branches that combine modality-specific features into fused ones and/or carry information across the branches.

    “A very common architectural choice is to adopt a multi-stream architecture for the encoder with a network branch processing each modality (e.g., a two-stream architecture for RGB and depth) and additional network modules connecting the different branches that combine modality-specific features into fused ones and/or carry information across the branches [98,99,101].”

    From Multimodal semantic segmentation in autonomous driving: A review of current approaches and future perspectives (2022) · cites this paper as [98]

  • Most recent approaches try to get the best of the three modalities by performing multiple fusion operations at different stages of the deep network.

    “However, most recent approaches try to get the best of the three modalities by performing multiple fusion operations at different stages of the deep network [98,115,118].”

    From Multimodal semantic segmentation in autonomous driving: A review of current approaches and future perspectives (2022) · cites this paper as [98]

  • SSMA, using a ResNet50 backbone, achieves an mIoU of 83.29 on the Cityscapes dataset for 2.5D semantic segmentation.

    “| SSMA [98] | ResNet50 [16] | 83.29 |”

    From Multimodal semantic segmentation in autonomous driving: A review of current approaches and future perspectives (2022) · cites this paper as [98]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 25

  1. Boniardi F, Valada A, Mohan R, Caselitz T, Burgard W (2019) Robot localization in floor plans using a room layout edge extraction network. arXiv preprint arXiv:190301804
  2. Chattopadhyay A, Sarkar A, Howlader P, Balasubramanian VN (2017) Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. arXiv preprint arXiv:171011063
  3. Chen L, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2016) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arxiv preprint arXiv: 160600915
  4. Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:170605587
  5. Chollet F (2016) Xception: Deep learning with depthwise separable convolutions. arXiv preprint arXiv:161002357
  6. Couprie C, Farabet C, Najman L, LeCun Y (2013) Indoor semantic segmentation using depth information. arXiv preprint arXiv:13013572
  7. Dai A, Nießner M (2018) 3dmv: Joint 3d-multi-view prediction for 3d semantic scene segmentation. arXiv preprint arXiv:180310409
  8. Grangier D, Bottou L, , Collobert R (2009) Deep convolutional networks for scene parsing. In: ICML Workshop on Deep Learning
  9. Hu J, Shen L, Sun G (2017) Squeeze-and-excitation networks. arXiv preprint arXiv:170901507
  10. Ku J, Harakeh A, Waslander SL (2018) In defense of classical image processing: Fast depth completion on the cpu. arXiv preprint arXiv:180200036
  11. LeCun Y, Denker JS, Solla SA (1990) Optimal brain damage. In: Advances in neural information processing systems, pp 598-605
  12. Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2017) Pruning filters for efficient convnets. Proceedings of the International Conference on Learning Representations
  13. Liang-Chieh C, Papandreou G, Kokkinos I, Murphy K, Yuille A (2015) Semantic image segmentation with deep convolutional nets and fully connected crfs. In: International Conference on Learning Representations
  14. Lin M, Chen Q, Yan S (2013) Network in network. arXiv preprint arXiv:13124400
  15. Liu W, Rabinovich A, Berg AC (2015) Parsenet: Looking wider to see better. arXiv preprint arXiv: 150604579
  16. Noh H, Araujo A, Sim J, Weyand T, Han B (2017) Largescale image retrieval with attentive deep local features. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3456-3465
  17. Paszke A, Chaurasia A, Kim S, Culurciello E (2016) Enet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:160602147
  18. Radwan N, Valada A, Burgard W (2018a) Multimodal interaction-aware motion prediction for autonomous street crossing. arXiv preprint arXiv:180806887
  19. Ren X, Bo L, Fox D (2012) Rgb-(d) scene labeling: Features and algorithms. In: Proceedings of the Conference on Computer Vision and Pattern Recognition
  20. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556
  21. Valada A, Dhall A, Burgard W (2016a) Convoluted mixture of deep experts for robust semantic segmentation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Workshop, State Estimation and Terrain Perception for All Terrain Mobile Robots
  22. Valada A, Oliveira G, Brox T, Burgard W (2016c) Towards robust semantic segmentation using deep fusion. In: Robotics: Science and Systems (RSS 2016) Workshop, Are the Sceptics Right? Limits and Potentials of Deep Learning in Robotics
  23. Wen W, Wu C, Wang Y, Chen Y, Li H (2016) Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp 2074-2082
  24. Xiang Y, Fox D (2017) Da-rnn: Semantic mapping with data associated recurrent neural networks. arXiv preprint arXiv:170303098
  25. Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2014) Object detectors emerge in deep scene cnns. arXiv preprint arXiv:14126856

Cited by

Sorted by citations

Authors
Valada, A., Mohan, R., & Burgard, W.
Affiliations
University of Freiburg (DE)
Corresponding author
Valada, Abhinav
ORCID
Venue
International Journal of Computer Vision
Publisher
Springer Science and Business Media LLC
Published
2019-07-08
Volume
128
Issue
5
Pages
1239-1285
ISSN
  • 0920-5691 (ISSN-L)
  • 1573-1405
DOI
10.1007/s11263-019-01188-y
OpenAlex
W2956887593
Cited by
293
References
60
Citations by year
2026: 24 · 2025: 35 · 2024: 41 · 2023: 45 · 2022: 45 · 2021: 65 · 2020: 26 · 2019: 12
FWCI
16.56
Type
journal article
Language
en
Open access
Licence
Locations
  • International Journal of Computer Vision (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • FreiDok plus (Universitätsbibliothek Freiburg) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
feature fusion, attention mechanism, atrous spatial pyramid pooling

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