Log In Sign Up

Robust Trust Region for Weakly Supervised Segmentation

by   Dmitrii Marin, et al.

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.


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

Weakly supervised segmentation requires assigning a label to every pixel...

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

Pixel-level annotations are expensive and time consuming to obtain. Henc...

On Regularized Losses for Weakly-supervised CNN Segmentation

Minimization of regularized losses is a principled approach to weak supe...

Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation

We focus on tackling weakly supervised semantic segmentation with scribb...

3D Spatial Recognition without Spatially Labeled 3D

We introduce WyPR, a Weakly-supervised framework for Point cloud Recogni...

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

We present a novel approach to train pixel resolution segmentation model...

ADM for grid CRF loss in CNN segmentation

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