ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
Open accessAbstract
Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major challenge. In numerous real-world applications, there is indeed a large gap between data distributions in train and test domains, which results in severe performance loss at run-time. In this work, we address the task of unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions. To this end, we propose two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively. We demonstrate state-of-the-art performance in semantic segmentation on two challenging “synthetic-2-real” set-ups and show that the approach can also be used for detection.
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.
Integrity signals
Registry
Cites
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.
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?
Several UDA approaches are not specifically designed for UDA in satellite pose estimation because the domain-agnostic geometrical constraints are not fully explored.
“Nonetheless, these methods are not specifically designed for UDA in satellite pose estimation, since the domain-agnostic geometrical constraints are not fully explored.”
From Bridging the Domain Gap in Satellite Pose Estimation: A Self-Training Approach Based on Geometrical Constraints (2024) · cites this paper as [20]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 52 · Cited by 1,524
Research works printed but not linked: 9
- [10][10] Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In ICML , 2015. 1, 2 -
- [11][11] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In NIPS , 2014. 3, 4 -
- [14][14] J. Hoffman, E. Tzeng, T. Park, J.-Y. Zhu, P. Isola, K. Saenko, A. Efros, and T. Darrell. CyCADA: Cycle-consistent adversarial domain adaptation. In ICML , 2018. 1, 2, 5, 6, 7 -
- [21][21] D.-H. Lee. Pseudo-label: The simple and efficient semisupervised learning method for deep neural networks. In ICML Workshop , 2013. 3 -
- [28][28] A. Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR , 2016. 5 -
- [32][32] K. Saito, Y. Ushiku, T. Harada, and K. Saenko. Adversarial dropout regularization. In ICLR , 2018. 1, 2 -
- [37][37] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR , 2015. 5, 8 -
- [38][38] J. T. Springenberg. Unsupervised and semi-supervised learning with categorical generative adversarial networks. ICLR , 2016. 2, 3 -
- [51][51] Y. Zou, Z. Yu, B. V. Kumar, and J. Wang. Unsupervised domain adaptation for semantic segmentation via classbalanced self-training. In ECCV , 2018. 1, 2, 3, 4, 5, 6, 7 Figure 3: Qualitative results in the GTA5 → Cityscapes set-up . Column (a) shows a input image and the corresponding semantic segmentation ground-truth. Column (b), (c) and (d) show segmentation results (bottom) along with prediction entropy maps produced by different approaches (top). Best viewed in colors. <!-- image --> Figure 4: Qualitative results for object detection. Column (a) shows the input images. Columns (b), (c) and (d) illustrate detection results of the baseline, our MinEnt and AdvEnt models. Detections of different classes are plotted in different colors. We visualize all the detections with scores greater than 0 . 5 . <!-- image -->
- Authors
- Vu, T.-H., Jain, H., Bucher, M., Cord, M., & Perez, P.
- Affiliations
- Valeo.ai
- Sorbonne Université (FR)
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 2512-2521
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2902727564
- Cited by
- 1,524
- References
- 52
- Citations by year
- 2026: 113 · 2025: 197 · 2024: 267 · 2023: 299 · 2022: 270 · 2021: 249 · 2020: 111 · 2019: 18
- FWCI
- 61.98
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- unsupervised domain adaptation, semantic segmentation, entropy loss, adversarial loss, domain shift, synthetic-to-real transfer, object detection
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
