DeepAI AI Chat
Log In Sign Up

Region-based semantic segmentation with end-to-end training

by   Holger Caesar, et al.

We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0 49.9


page 2

page 9

page 12


Semantic segmentation of mFISH images using convolutional networks

Multicolor in situ hybridization (mFISH) is a karyotyping technique used...

Semantic Segmentation with Labeling Uncertainty and Class Imbalance

Recently, methods based on Convolutional Neural Networks (CNN) achieved ...

Semantic Correlation Promoted Shape-Variant Context for Segmentation

Context is essential for semantic segmentation. Due to the diverse shape...

Actor-Action Semantic Segmentation with Region Masks

In this paper, we study the actor-action semantic segmentation problem, ...

End-to-End Egospheric Spatial Memory

Spatial memory, or the ability to remember and recall specific locations...

Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming

Reducing the use of agrochemicals is an important component towards sust...

Pixel-wise Attentional Gating for Parsimonious Pixel Labeling

To achieve parsimonious inference in per-pixel labeling tasks with a lim...