Constrained‐CNN losses for weakly supervised segmentation☆ (2018-05-12T00:00:00.000000Z)

TL;DR

A differentiable penalty is proposed, which enforces inequality constraints directly in the loss function, avoiding expensive Lagrangian dual iterates and proposal generation and has the potential to close the gap between weakly and fully supervised learning in semantic medical image segmentation.

Authors

Yuri Boykov

2 papers

Ismail Ben Ayed

11 papers

J. Dolz

14 papers

H. Kervadec

3 papers

Meng Tang

1 papers

Eric Granger

1 papers

TL;DR

Authors

References54 items

Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training

Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training

Normalized Cut Loss for Weakly-Supervised CNN Segmentation

On Regularized Losses for Weakly-supervised CNN Segmentation

Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision

Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction

Automatic differentiation in PyTorch

Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation

Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation

Imposing Hard Constraints on Deep Networks: Promises and Limitations

A survey on deep learning in medical image analysis

Constrained Deep Weak Supervision for Histopathology Image Segmentation

FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics

3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Learning under Distributed Weak Supervision

DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation

STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation

Train faster, generalize better: Stability of stochastic gradient descent

Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

Learning to segment under various forms of weak supervision

What's the Point: Semantic Segmentation with Point Supervision

U-Net: Convolutional Networks for Biomedical Image Segmentation

Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

Fully Convolutional Multi-Class Multiple Instance Learning

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

From image-level to pixel-level labeling with Convolutional Networks

Fully convolutional networks for semantic segmentation

Tell Me What You See and I Will Show You Where It Is

Efficient Energy Minimization for Enforcing Label Statistics

Fast Trust Region for Segmentation

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

Segmentation with area constraints

Weakly supervised structured output learning for semantic segmentation

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

A convex framework for image segmentation with moment constraints

Weakly supervised semantic segmentation with a multi-image model

Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning

Deep learning via semi-supervised embedding

Region Classification with Markov Field Aspect Models

"GrabCut": interactive foreground extraction using iterated graph cuts

Lagrange programming neural networks

Semi-supervised multi-organ segmentation via multi-planar co-training

Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part II

Deep Learning

Semi-Supervised Learning (Adaptive Computation and Machine Learning Series)

Constrained Differential Optimization

Field of Study

Journal Information

Name

Page

Volume