Publication
Annotation-efficient image anomaly detection
Related publications (33)
Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods
Michaël Unser, Dimitris Perdios, Pakshal Narendra Bohra, Alexis Marie Frederic Goujon, Sébastien Alexandre Emery
Ill-posed linear inverse problems are frequently encountered in image reconstruction tasks. Image reconstruction methods that combine the Plug-and-Play (PnP) priors framework with convolutional neural network (CNN) based denoisers have shown impressive per ...
2021Learning Approach to Delineation of Curvilinear Structures in 2D and 3D Images
Detection of curvilinear structures has long been of interest due to its wide range of applications. Large amounts of imaging data could be readily used in many fields, but it is practically not possible to analyze them manually. Hence, the need for automa ...
EPFL2019Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
Michaël Unser, Michael Thompson McCann
This tutorial covers biomedical image reconstruction, from the foundational concepts of system modeling and direct reconstruction to modern sparsity and learning-based approaches. Imaging is a critical tool in biological research and medicine, and most ima ...
2019Deep Unfolding for Communications Systems: A Survey and Some New Directions
Alexios Konstantinos Balatsoukas Stimming, Christoph Studer
Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey sum ...
IEEE2019Evaluating and Interpreting Deep Convolutional Neural Networks via Non-negative Matrix Factorization
With ever greater computational resources and more accessible software, deep neural networks have become ubiquitous across industry and academia.
Their remarkable ability to generalize to new samples defies the conventional view, which holds that complex, ...
EPFL2019Large-Scale Image Segmentation with Convolutional Networks
Pedro Henrique Oliveira Pinheiro
Object recognition is one of the most important problems in computer vision. However, visual recognition poses many challenges when tried to be reproduced by artificial systems. A main challenge is the problem of variability: objects can appear across huge ...
EPFL2017Large-Scale Image Segmentation with Convolutional Networks
Pedro Henrique Oliveira Pinheiro
Object recognition is one of the most important problems in computer vision. However, visual recognition poses many challenges when tried to be reproduced by artificial systems. A main challenge is the problem of variability: objects can appear across huge ...
Sciences et Techniques de l’Ingénieur (STI)2017Learning to Refine Object Segments
Ronan Collobert, Pedro Henrique Oliveira Pinheiro
Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode object-level knowledge b ...
Springer2016From Image-level to Pixel-level Labeling with Convolutional Networks
Ronan Collobert, Pedro Henrique Oliveira Pinheiro
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation task, and natur ...
2015Music Learning with Long Short Term Memory Networks
Humans are able to learn and compose complex, yet beautiful, pieces of music as seen in e.g. the highly complicated works of J.S. Bach. However, how our brain is able to store and produce these very long temporal sequences is still an open question. Long s ...
2015