Loss Max-Pooling for Semantic Image Segmentation
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them. Our method adaptively re-weights the contributions of each pixel based on their observed losses, targeting under-performing classification results as often encountered for under-represented object classes. Our approach goes beyond conventional cost-sensitive learning attempts through adaptive considerations that allow us to indirectly address both, inter- and intra-class imbalances. We provide a theoretical justification of our approach, complementary to experimental analyses on benchmark datasets. In our experiments on the Cityscapes and Pascal VOC 2012 segmentation datasets we find consistently improved results, demonstrating the efficacy of our approach.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 1×
“SMOTE and derived variants [6, 8, 19, 24] on ways to avoid over-fitting).”
MethodSegNet: 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
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 5×
“We have evaluated our novel loss max-pooling ( LMP ) approach on the Cityscapes [10] and the extended Pascal VOC [14] semantic image segmentation datasets.”
MethodInfluentialMulti-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 2×
“In particular, we are using ResNet-101 [21] in a fully-convolutional way with atrous extensions [22, 46] for the base layers before adding DeepLab’s atrous spatial pyramid pooling (ASPP).”
BackgroundMethodThe 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 · cited 1×
“We additionally assess the quality of our novel LMP on the Pascal VOC 2012 segmentation benchmark dataset [13], comprising 20 object classes and a background class.”
MethodBorderline-SMOTE : A New Over-Sampling Method in Imbalanced Data Sets Learning
Han, H., Wang, W.-Y., & Mao, B.-H. (2005) · Lecture notes in computer science · doi:10.1007/11538059_91 · Cited by 4,331
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Eigen, D., & Fergus, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.304 · Cited by 2,862 · cited 5×
“39]. Related Works. Many semantic segmentation works follow a relatively simple cost-sensitive approach via an inverse frequency rebalancing scheme, e.g. [7,35,44,45] or median frequency re-weighting [12]. Other approaches construct best-practice heuristics by e.g. restricting the number of pixels to be updated during…”
BackgroundMethodInfluentialTraining Region-Based Object Detectors with Online Hard Example Mining
Shrivastava, A., Gupta, A., & Girshick, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.89 · Cited by 2,686
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., & Dollár, P. (2014) · arXiv · doi:10.48550/arxiv.1405.0312 · Cited by 2,579
Conditional Random Fields as Recurrent Neural Networks
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.179 · Cited by 2,386 · cited 1×
“Extending CNNs to directly cast dense, semantic label maps [2, 34], including more contextual information [9, 16, 33, 46] or refining results with graphical models [31, 47], have led to impressive results in many realworld applications and on standard benchmark datasets.”
BackgroundThe 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) · arXiv · doi:10.48550/arxiv.1604.01685 · Cited by 1,174
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Lin, G., Shen, C., van den Hengel, A., & Reid, I. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.348 · Cited by 862
Learning to Localize Objects with Structured Output Regression
Blaschko, M. B., & Lampert, C. H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_2 · Cited by 324 · cited 1×
“In separate though related research fields, focus was put on directly optimizing the target measures like Area under curve (AUC), Intersection over Union (IoU or Jaccard Index) or Average class (AC) [1, 4, 36, 37].”
BackgroundGeoF: Geodesic Forests for Learning Coupled Predictors
Kontschieder, P., Kohli, P., Shotton, J., & Criminisi, A. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.16 · Cited by 63 · cited 1×
“Such methods were recently investigated [7, 35, 44, 45] for deep learning, some of them following ideas previously applied in shallow learning methods like random forests [27, 28] or support vector machines [38, 42].”
MethodInfluentialSelf-citation
Cited by
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
“A common solution is to perform some form of hard negative mining [17], [19], [20], [16], [9] that samples hard examples during training or more complex sampling/reweighing schemes [34].”
BackgroundFocal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Neuhold, G., Ollmann, T., Bulo, S. R., & Kontschieder, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.534 · Cited by 1,434
Self-citationFeature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
Yang, F., Zhang, L., Yu, S., Prokhorov, D., Mei, X., & Ling, H. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2910595 · Cited by 1,226
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Hou, Q., Zhang, L., Cheng, M.-M., & Feng, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00406 · Cited by 820
Metadata
- Authors
- Bulo, S. R., Neuhold, G., & Kontschieder, P.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 7082-7091
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2607180574
- Cited by
- 143
- References
- 17
- FWCI
- 6.39
- Type
- conference paper
- Language
- en
- Open access
- green
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.