DeepAI
Log In Sign Up

Robust Trust Region for Weakly Supervised Segmentation

04/05/2021
by   Dmitrii Marin, et al.
0

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses - originally developed for unsupervised low-level segmentation and representing geometric priors on pixel labels - can considerably improve the quality of weakly supervised training. However, many common priors require optimization stronger than gradient descent. Thus, such regularizers have limited applicability in deep learning. We propose a new robust trust region approach for regularized losses improving the state-of-the-art results. Our approach can be seen as a higher-order generalization of the classic chain rule. It allows neural network optimization to use strong low-level solvers for the corresponding regularizers, including discrete ones.

READ FULL TEXT
05/03/2021

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Weakly supervised segmentation requires assigning a label to every pixel...
06/06/2017

Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation

Pixel-level annotations are expensive and time consuming to obtain. Henc...
03/26/2018

On Regularized Losses for Weakly-supervised CNN Segmentation

Minimization of regularized losses is a principled approach to weak supe...
08/03/2021

Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation

We focus on tackling weakly supervised semantic segmentation with scribb...
05/13/2021

3D Spatial Recognition without Spatially Labeled 3D

We introduce WyPR, a Weakly-supervised framework for Point cloud Recogni...
05/30/2019

Weakly supervised training of pixel resolution segmentation models on whole slide images

We present a novel approach to train pixel resolution segmentation model...
09/07/2018

ADM for grid CRF loss in CNN segmentation

Variants of gradient descent (GD) dominate CNN loss minimization in comp...