Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation

Richmond, David L.; Kainmueller, Dagmar; Yang, Michael Ying; Myers, Eugene W.; Rother, Carsten

doi:10.5244/c.30.144

Cited by 13 publications

(11 citation statements)

References 33 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Going further along this path, it may be interesting to revisit existing works on the equivalence between CNN and auto-context random forests [40] in order to find a better trade-off between the ability to automatically extract contextual features and the computational complexity acceptable in an operational map production system.…”

Section: Discussionmentioning

confidence: 99%

Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

et al. 2019

View full text Add to dashboard Cite

The Sentinel-2 satellite mission offers high resolution multispectral time-series image data, enabling the production of detailed land cover maps globally. When mapping large territories, the trade-off between processing time and result quality is a central design decision. Currently, this machine learning task is usually performed using pixel-wise classification methods. However, the radical shift of the computer vision field away from hand-engineered image features and towards more automation by representation learning comes with many promises, including higher quality results and less engineering effort. In particular, convolutional neural networks learn features which take into account the context of the pixels and, therefore, a better representation of the data can be obtained. In this paper, we assess fully convolutional neural network architectures as replacements for a Random Forest classifier in an operational context for the production of high resolution land cover maps with Sentinel-2 time-series at the country scale. Our contributions include a framework for working with Sentinel-2 L2A time-series image data, an adaptation of the U-Net model (a fully convolutional neural network) for dealing with sparse annotation data while maintaining high resolution output, and an analysis of those results in the context of operational production of land cover maps. We conclude that fully convolutional neural networks can yield improved results with respect to pixel-wise Random Forest classifiers for classes where texture and context are pertinent. However, this new approach shows higher variability in quality across different landscapes and comes with a computational cost which could be to high for operational systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

et al. 2019

View full text Add to dashboard Cite

show abstract

“…As long as the structure of the trees is preserved, the optimized parameters of the neural network can also be mapped back to the random forest. Subsequently, [25] cast stacked decision forests to convolutional neural networks and found an approximate mapping back. In [9,17] several models of neural networks with separate, conditional data flows are discussed.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Learning of Deterministic Decision Trees

Hehn

Hamprecht

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data. However, they lack a key quality that has helped fuel the deep learning revolution: that of being end-to-end trainable, and to learn from scratch those features that best allow to solve a given supervised learning problem. Recent work (Kontschieder 2015) has addressed this deficit, but at the cost of losing a main attractive trait of decision trees: the fact that each sample is routed along a small subset of tree nodes only. We here propose a model and Expectation-Maximization training scheme for decision trees that are fully probabilistic at train time, but after a deterministic annealing process become deterministic at test time. We also analyze the learned oblique split parameters on image datasets and show that Neural Networks can be trained at each split node. In summary, we present the first endto-end learning scheme for deterministic decision trees and present results on par with or superior to published standard oblique decision tree algorithms.

show abstract

“…50 Deep learning algorithms can also benefit from accurate segmentation information provided by 7T MRI for improving feature learning. 51 Although our method produces better segmentation results, it has some limitations. (1) The number of training subjects (with both 3 and 7T MR images) is small in our experiments.…”

Section: Discussionmentioning

confidence: 98%