ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation

@article{Siddiqui2020ViewALAL,
  title={ViewAL: Active Learning With Viewpoint Entropy for Semantic Segmentation},
  author={Yawar Siddiqui and Julien P. C. Valentin and Matthias Nie{\ss}ner},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={9430-9440}
}
We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable measure of uncertainty and encourage the model to perform well irrespective of the viewpoint under which objects are observed. To incorporate this uncertainty measure, we introduce a new viewpoint entropy formulation, which is the basis of our active learning… Expand
16 Citations
All you need are a few pixels: semantic segmentation with PixelPick
  • PDF
Importance of Self-Consistency in Active Learning for Semantic Segmentation
  • 1
  • Highly Influenced
  • PDF
DEAL: Difficulty-aware Active Learning for Semantic Segmentation
  • 2
  • PDF
3D Semantic Labeling of Photogrammetry Meshes Based on Active Learning
  • Mengqi Rong, Shuhan Shen, Zhanyi Hu
  • Computer Science
  • 2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
Dual Adversarial Network for Deep Active Learning
  • PDF
Semantic Curiosity for Active Visual Learning
  • 7
  • PDF
Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VI
  • Highly Influenced
Active machine learning for spatio-temporal predictions using feature embedding
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 66 REFERENCES
Active learning for semantic segmentation with expected change
  • 99
  • PDF
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
  • 13,523
  • PDF
CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
  • 33
  • Highly Influential
  • PDF
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  • 6,744
  • PDF
Cost-Effective Active Learning for Deep Image Classification
  • 295
  • Highly Influential
  • PDF
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
  • 841
  • PDF
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
  • 2,907
  • PDF
Multi-view multi-label active learning for image classification
  • 32
  • PDF
Multi-class active learning for image classification
  • 184
  • PDF
...
1
2
3
4
5
...