The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Complementary Random Masking for RGB-Thermal Semantic Segmentation
Open accessAbstract
RGB-thermal semantic segmentation is one potential solution to achieve reliable semantic scene understanding in adverse weather and lighting conditions. However, the previous studies mostly focus on designing a multi-modal fusion module without consideration of the nature of multi-modality inputs. Therefore, the networks easily become over-reliant on a single modality, making it difficult to learn complementary and meaningful representations for each modality. This paper proposes 1) a complementary random masking strategy of RGB-T images and 2) self-distillation loss between clean and masked input modalities. The proposed masking strategy prevents over-reliance on a single modality. It also improves the accuracy and robustness of the neural network by forcing the network to segment and classify objects even when one modality is partially available. Also, the proposed self-distillation loss encourages the network to extract complementary and meaningful representations from a single modality or complementary masked modalities. We achieve state-of-the-art performance over three RGB-T semantic segmentation benchmarks. Our source code is available at https://github.com/UkcheolShin/CRM_RGBTSeg.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
In the citing paper
“The resulting adaptation offers significant savings compared to training a separate model for each input combination or retraining the model using some specialized training strategy like modality dropout [18, 17] or knowledge distillation [20, 22].”
From Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation (2025) · cites this paper as [20]
In the citing paper
“The current methods for robust MML, as discussed in Section 2, require retraining the whole model with specialized training strategy [20, 18] or utilize extra module/sub-network to guide the multi-modal model [22, 21].”
From Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation (2025) · cites this paper as [20]
In the citing paper
“The parameter complexity of our approach is comparable/better than existing robust methods like CRM [20] in Table 2 and prompts [27] in Table 6.”
From Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation (2025) · cites this paper as [20]
In the citing paper
“Among the robust models, complementary random masking and knowledge distillation based model CRM [20] shows competitive performance with the Adapted model.”
From Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation (2025) · cites this paper as [20]
In the citing paper
“Notably CRM is designed specifically for RGB-Thermal pairs and requires specialized training approach.”
From Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation (2025) · cites this paper as [20]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 2×
“Recently, masking strategy has been widely utilized in various language [9], [23], [2] and visual applications [1], [12], [41], [38], [43], [28] to learn meaningful representation.”
BackgroundMethodSelf-citationBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Self-citationImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · cited 3×
“We use Swin-Transformer [24] as our backbone model.”
Method(2016) · Cited by 31,590
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“Our proposed method is implemented with PyTorch [29] and Detectron2 [42] library on a machine equipped with two NVIDIA RTX A6000 GPUs.”
MethodHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“Recently, masking strategy has been widely utilized in various language [9], [23], [2] and visual applications [1], [12], [41], [38], [43], [28] to learn meaningful representation.”
BackgroundChen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · cited 2×
“RGB-thermal semantic segmentation networks have also been proposed to overcome the limitation of RGB semantic segmentation networks [4], [13], [40], [6], [5] that are often vulnerable to extreme conditions, such as low-light, rainy, snowy, and sandy conditions.”
BackgroundMethodSSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 1×
“We apply random color jittering [22], random horizontal flipping, and random cropping to RGB and thermal images as data augmentation.”
Method
Research works printed but not linked: 1
- Wu, 2019, Detectron2
Cited by
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
Hou, X., Xing, J., Qian, Y., Guo, Y., Xin, S., Chen, J., Tang, K., Wang, M., Jiang, Z., Liu, L., et al. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02507 · Cited by 245
“Consequently, there is a growing interest in incorporating multimodal images to obtain more comprehensive information, which has also gained considerable attention in other areas such as object detection [23, 24, 46] and semantic segmentation [1– 3, 25, 37, 44, 68, 75], among others.”
BackgroundRobust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
Reza, M. K., Prater-Bennette, A., & Asif, M. S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3476487 · Cited by 78
“Unlike existing methods, we do not try to generate [39, 2], approximate [55, 54] or distill knowledge [48, 40] from any other modality/sub-network.”
BackgroundMethodInfluentialXoFTR: Cross-modal Feature Matching Transformer
Tuzcuoğlu, Ö., Köksal, A., Sofu, B., Kalkan, S., & Alatan, A. A. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00431 · Cited by 152
“Complementary Random Masking [68] targets RGB-Thermal segmentation with unique masking and self-distillation approach, reducing modality dependency.”
BackgroundHuang, J., Li, J., Ning, J., Sun, Y., Liu, C., Chen, Q., & Fan, R. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3448251 · Cited by 48
Caltech Aerial RGB-Thermal Dataset in the Wild
Lee, C., Anderson, M., Ranganathan, N., Zuo, X., Do, K., Gkioxari, G., & Chung, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73036-8_14 · Cited by 33
Metadata
- Authors
- Shin, U., Lee, K., Kweon, I. S., & Oh, J.
- Affiliations
- Carnegie Mellon University (US)
- Korea Advanced Institute of Science and Technology (KR)
- Venue
- 2024 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2024-05-13
- Pages
- 11110-11117
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W4401415581
- Cited by
- 49
- References
- 49
- Citations by year
- 2026: 14 · 2025: 25 · 2024: 9
- FWCI
- 9.88
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- Ministry of Trade, Industry and Energy
- Korea Institute for Advancement of Technology (P0019782, P0026022)
- 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 › Engineering › Media Technology › Advanced Image Fusion Techniques
- Keywords
- multimodal fusion, infrared thermography, multimodal representation learning
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Complementary Random Masking for RGB-Thermal Semantic Segmentation. https://app.cochat.ai/papers/10.1109/icra57147.2024.10611200
- The paper
- Shin, U., Lee, K., Kweon, I. S., & Oh, J. (2024). Complementary Random Masking for RGB-Thermal Semantic Segmentation. 2024 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra57147.2024.10611200
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.