Ensemble Knowledge Transfer for Semantic Segmentation
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Semantic segmentation networks are usually learned in a strictly supervised manner, i.e., they are trained and tested on similar data distributions. Performance drops drastically in the presence of domain shifts. In this paper, we explore methods for learning across train and test distributions that dramatically differ in scene structure, viewpoints, and objects statistics. Motivated by the proliferation of aerial drone robotics, we consider the target task of semantic segmentation from aerial viewpoints. Inspired by the impact of Cityscapes [11], we introduce AeroScapes, a new dataset of 3269 images of aerial scenes (captured with a fleet of drones) annotated with dense semantic segmentations. Our dataset differs from existing segmentation datasets (that focus on ground-view or indoorscene domains) in terms of viewpoint, scene composition, and object scales. We propose a simple but effective approach for transferring knowledge from such diverse domains (for which considerable annotated training data exists) to our target task. To do so, we train multiple models for aerial segmentation via progressive fine-tuning through each source domain. We then treat these collections of models as an ensemble that can be aggregated to significantly improve performance. We demonstrate large absolute improvements (8.12%) over widely-used standard baselines.
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.
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
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 7×
“marks have focused on limited viewpoints of specialized scenes such as ground-views of urban environments (for autonomous vehicles) [36, 11, 51], and direct overhead views (for orbital satellites) [41, 34, 23].”
BackgroundMethodInfluentialDomain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Rethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517 · cited 1×
“Semantic segmentation: Start-of-the-art semantic segmentation methods use the convolutional networks to learn a pixel-to-pixel mapping from the image space to semantic label space [30, 9, 50, 28, 27, 12].”
MethodThe Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“While transfer learning from a source to target task is a well studied problem [38, 49], by far the most common approach is fine-tuning a model pre-trained on the source task [18].”
BackgroundLearning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505 · cited 1×
“Recent deep learning-based methods align the domain features by maximizing the confusion [14, 15, 47] or explicitly minimizing the distances [31, 32] between their distributions across domain.”
MethodCatastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770
Scene Parsing through ADE20K Dataset
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.544 · Cited by 3,326
Cited by
Object-Contextual Representations for Semantic Segmentation
Yuan, Y., Chen, X., & Wang, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_11 · Cited by 1,285
Hossain, M. D., & Chen, D. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.02.009 · Cited by 697
Artificial Intelligence for Remote Sensing Data Analysis: A review of challenges and opportunities
Zhang, L., & Zhang, L. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3145854 · Cited by 604
Swin Transformer Embedding UNet for Remote Sensing Image Semantic Segmentation
He, X., Zhou, Y., Zhao, J., Zhang, D., Yao, R., & Xue, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3144165 · Cited by 550
UAVid: A semantic segmentation dataset for UAV imagery
Lyu, Y., Vosselman, G., Xia, G.-S., Yilmaz, A., & Yang, M. Y. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.05.009 · Cited by 424
On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances, and Million-AID
Long, Y., Xia, G.-S., Li, S., Yang, W., Yang, M. Y., Zhu, X. X., Zhang, L., & Li, D. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3070368 · Cited by 250
Balamuralidhar, N., Tilon, S., & Nex, F. (2021) · Remote Sensing · doi:10.3390/rs13040573 · Cited by 104
“The Aeroscapes dataset is an aerial semantic segmentation benchmark dataset that was collected using a DJI Phantom 3 fleet of drones between the altitudes of 5 and 50 m [78].”
Method
Metadata
- Authors
- Nigam, I., Huang, C., & Ramanan, D.
- Venue
- 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2018-03
- Pages
- 1499-1508
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2799785415
- Cited by
- 117
- References
- 26
- FWCI
- 2.91
- Type
- conference paper
- Language
- en
- Open access
- closed
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.