• Corpus ID: 195750604

A multi-task U-net for segmentation with lazy labels

  title={A multi-task U-net for segmentation with lazy labels},
  author={Rihuan Ke and Aur{\'e}lie Bugeau and Nicolas Papadakis and Peter Sch{\"u}tz and Carola-Bibiane Sch{\"o}nlieb},
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for image segmentation. [...] Key Method Image segmentation is then stratified into three connected tasks: rough detection of class instances, separation of wrongly connected objects without a clear boundary, and pixel-wise segmentation to find the accurate boundaries of each object.Expand
An anatomically-informed 3D CNN for brain aneurysm classification with weak labels
This work addresses the task of brain aneurysm detection as a patch-wise binary classification with weak labels, in contrast to related studies that rather use supervised segmentation methods and voxel-wise delineations.
LR-Net: A Multi-task Model Using Relationship-based Contour Information to Enhance the Semantic Segmentation of Cancer Regions
A multi-task learning technique to enhance the importance of contours and increase the weight of pixels relationship learning for the tumor segmentation is developed and Experimental results show that LR-Net is superior to many popular approaches, such as CE-Net and U-Net.
Machine Learning towards General Medical Image Segmentation
The quality of patient care associated with diagnostic radiology is proportionate to a physician’s workload. Segmentation is a fundamental limiting precursor to diagnostic and therapeutic procedures.
Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency
This paper presents a model that is able to provide visual clues for human experts to understand and justify for their own recognition process, and shows how this model can be used to test different hypothesis of the copper surface response to different manufacturing processes.
Application of Artificial Neural Networks for Analysis of Ice Recrystallization Process for Cryopreservation
The obtained results show the possibility of segmentation of ice crystals in cryomicroscopic images taking into account the overlapping of intensity levels of an object and background.
A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
This work proposes a holistic solution framed as a three-stage self-training framework for semi-supervised semantic segmentation that decreases uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion.
Deep semantic segmentation of natural and medical images: a review
This review categorizes the leading deep learning-based medical and non-medical image segmentation solutions into six main groups of deep architectural, data synthesis- based, loss function-based, sequenced models, weakly supervised, and multi-task methods.


Coarse-to-Fine Semantic Segmentation From Image-Level Labels
This paper proposes a novel recursive coarse-to-fine semantic segmentation framework based on only image-level category labels that can be easily extended to foreground object segmentation task and achieves comparable performance with the state-of-the-art supervised methods on the Internet object dataset.
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
A simple to complex (STC) framework in which only image-level annotations are utilized to learn DCNNs for semantic segmentation, which demonstrates the superiority of the proposed STC framework compared with other state-of-the-arts frameworks.
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort.
A Novel Weakly Supervised Multitask Architecture for Retinal Lesions Segmentation on Fundus Images
A novel approach for training a convolutional multi-task architecture with supervised learning and reinforcing it with weakly supervised learning is proposed and the advantages of a new preprocessing method that guarantees the color consistency between the raw image and its enhanced version are discussed.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
The decoupled architecture enables the algorithm to learn classification and segmentation networks separately based on the training data with image-level and pixel-wise class labels, respectively, and facilitates to reduce search space for segmentation effectively by exploiting class-specific activation maps obtained from bridging layers.
A Multitask Learning Architecture for Simultaneous Segmentation of Bright and Red Lesions in Fundus Images
This work proposes an extension to the U-Net architecture relying on multi-task learning: while keeping a single encoding module, multiple decoding modules are used for concurrent segmentation tasks and proposes improvements of the encoding module based on the latest CNN developments.
Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells
Two novel weight maps applied to the weighted cross entropy loss function are presented which take into account both class imbalance and cell geometry and show superior results when compared to other similar schemes, outperforming binary class models with significant improvement of boundary adequacy and instance detection.
Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing
This paper proposes to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing, and obtains the state-of-the-art performance.
Deep learning with mixed supervision for brain tumor segmentation
This work proposes to use both types of training data (fully annotated and weakly annotated) to train a deep learning model for segmentation and shows that the proposed approach provides a significant improvement in segmentation performance compared to the standard supervised learning.