Shearlets as feature extractor for semantic edge detection: the model-based and data-driven realm

@article{AndradeLoarca2020ShearletsAF,
  title={Shearlets as feature extractor for semantic edge detection: the model-based and data-driven realm},
  author={H{\'e}ctor Andrade-Loarca and G. Kutyniok and O. {\"O}ktem},
  journal={Proceedings. Mathematical, Physical, and Engineering Sciences},
  year={2020},
  volume={476}
}
Semantic edge detection has recently gained a lot of attention as an image-processing task, mainly because of its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detection and edge classification. Those are in fact fundamentally distinct in terms of the level of abstraction that each task requires. This fact is known as the distracted supervision paradox… Expand
7 Citations
Multi-scale spatial context-based semantic edge detection
TLDR
This paper presents a Multi-scale Spatial Context-based deep network for Semantic Edge Detection (MSC-SED), which outperforms state-of-the-art approaches in terms of both the edge quality and the accuracy of edge classification on both the SBD and Cityscapes datasets. Expand
Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets
TLDR
Wavelet transformation and spectral methods are used to analyze the contents of image classification datasets, extract specific patterns from the datasets and find the associations between patterns and classes, revealing disassociation of patterns from classes, when images are randomly labeled. Expand
A novel reconstruction technique for two-dimensional Bragg scatter imaging
TLDR
A new reconstruction technique for two-dimensional Bragg Scattering Tomography, based on the Radon transform models of 2004, which captures both the Bragg scatter effects described by BST as well as beam attenuation and Compton scatter is introduced. Expand
A joint reconstruction and lambda tomography regularization technique for energy-resolved x-ray imaging
TLDR
A novel microlocal analysis of the parallel line geometry is presented which explains the nature of image artefacts when the attenuation coefficient and electron density are reconstructed separately and a new joint reconstruction scheme for low effective $Z$ (atomic number) imaging characterized by a regularization strategy whose structure is derived from lambda tomography principles and motivated directly by the microlocal analytic results. Expand
Federated Learning without Revealing the Decision Boundaries
TLDR
A method to encrypt the images, and have a decryption module hidden inside the model so that the entity in charge of federated learning will not see the training images and they will not know the location of the decision boundaries of the model. Expand
Shearlets: From Theory to Deep Learning
Bragg scattering tomography
Here we introduce a new forward model and imaging modality for Bragg Scattering Tomography (BST). The model we propose is based on an X-ray portal scanner with linear detector collimation, currentlyExpand

References

SHOWING 1-10 OF 61 REFERENCES
CASENet: Deep Category-Aware Semantic Edge Detection
TLDR
This work proposes a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features. Expand
Semantic Edge Detection with Diverse Deep Supervision
TLDR
A novel fully convolutional neural network architecture using diverse deep supervision (DDS) within a multi-task framework where lower layers aim at generating category-agnostic edges, while higher layers are responsible for the detection of category-aware semantic edges. Expand
Richer Convolutional Features for Edge Detection
TLDR
RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation, and achieves state-of-the-art performance on several available datasets. Expand
Richer Convolutional Features for Edge Detection
TLDR
The proposed network fully exploits multiscale and multilevel information of objects to perform the image-to-image prediction by combining all the meaningful convolutional features in a holistic manner and achieves state-of-the-art performance on several available datasets. Expand
Simultaneous Edge Alignment and Learning
TLDR
It is shown that label misalignment can cause considerably degraded edge learning quality, and a probabilistic model is formulated where edge alignment is treated as latent variable optimization, and is learned end-to-end during network training. Expand
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection
TLDR
This work claims that recognizing objects and predicting contours are two mutually related tasks, and shows that it can invert the commonly established pipeline: instead of detecting contours with low-level cues for a higher-level recognition task, it exploits object-related features as high- level cues for contour detection. Expand
On Edge Detection
  • V. Torre, T. Poggio
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1986
TLDR
It is shown that numerical differentiation of images is an ill-posed problem in the sense of Hadamard, and that this part of edge detection consists of two steps, a filtering step and a differentiation step. Expand
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
TLDR
A hierarchical deep model is introduced which produces more rich and complementary representations and the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed to refine and robustly fuse the representations learned at different scales. Expand
tfShearlab: The TensorFlow Digital Shearlet Transform for Deep Learning
TLDR
This paper developed a tensor shearlet transform aiming to provide a faithful TensorFlow implementation, and observed an significant improvement in the performance of the transform, with a running time of almost 40 times the previous state-of-the-art implementation. Expand
Semantic contours from inverse detectors
TLDR
A simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours is presented and a principled way of combining information from different part detectors and across categories is provided. Expand
...
1
2
3
4
5
...