Normalized Cut Loss for Weakly-supervised CNN Segmentation

Abstract

Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training. Common weakly-supervised approaches generate full masks from partial input (e.g. scribbles or seeds) using standard interactive segmentation methods as preprocessing. But, errors in such masks result in poorer training since standard loss functions (e.g. cross-entropy) do not distinguish seeds from potentially mislabeled other pixels. Inspired by the general ideas in semi-supervised learning, we address these problems via a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g. normalized cut. Unlike prior work, the cross entropy part of our loss evaluates only seeds where labels are known while normalized cut softly evaluates consistency of all pixels. We focus on normalized cut loss where dense Gaussian kernel is efficiently implemented in linear time by fast Bilateral filtering. Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods.

arXiv commentAccepted at CVPR 2018

References in corpus (4)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• On Regularized Losses for Weakly-supervised CNN Segmentation

Cited by in corpus (14)

• Constrained-CNN losses for weakly supervised segmentation
• Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• On Regularized Losses for Weakly-supervised CNN Segmentation
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
• Spectral Feature Transformation for Person Re-identification
• Temporally Distributed Networks for Fast Video Semantic Segmentation
• Min-max Entropy for Weakly Supervised Pointwise Localization
• Real-time Semantic Segmentation with Fast Attention
• Semi-supervised Skin Detection by Network with Mutual Guidance
• LID 2020: The Learning from Imperfect Data Challenge Results
• Simulating CRF with CNN for CNN
• A Macro-Micro Weakly-supervised Framework for AS-OCT Tissue Segmentation
• WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations