Deep Watershed Transform for Instance Segmentation
Min Bai,Raquel Urtasun +1 more
- pp 2858-2866
TLDR
This paper presents a simple yet powerful end-to-end convolutional neural network that achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.Abstract:
Most contemporary approaches to instance segmentation use complex pipelines involving conditional random fields, recurrent neural networks, object proposals, or template matching schemes. In this paper, we present a simple yet powerful end-to-end convolutional neural network to tackle this task. Our approach combines intuitions from the classical watershed transform and modern deep learning to produce an energy map of the image where object instances are unambiguously represented as energy basins. We then perform a cut at a single energy level to directly yield connected components corresponding to object instances. Our model achieves more than double the performance over the state-of-the-art on the challenging Cityscapes Instance Level Segmentation task.read more
Citations
More filters
Book ChapterDOI
Probabilistic Deep Learning for Instance Segmentation
TL;DR: This work proposes a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models and analyzes the quality of the uncertainty estimates with a metric adapted from semantic segmentation.
Proceedings ArticleDOI
Semantic Segmentation of Sheep Organs by Convolutional Neural Networks
TL;DR: This paper presents the first semantic segmentation method to localise and label sheep organs in images of the extracted organ package, trained to partition images into segments corresponding to individual organs.
Book ChapterDOI
A Differentiable Convolutional Distance Transform Layer for Improved Image Segmentation.
TL;DR: This paper proposes using a novel differentiable convolutional distance transform layer for segmentation networks such as U-Net to regularize the training process and addresses the problem of numerical instability for large images by presenting a cascaded procedure with locally restricted convolutionAL distance transforms.
Journal ArticleDOI
Semantics for Robotic Mapping, Perception and Interaction: A Survey
Sourav Garg,Niko Sünderhauf,Feras Dayoub,Douglas Morrison,Akansel Cosgun,Gustavo Carneiro,Qi Wu,Tat-Jun Chin,Ian Reid,Stephen Gould,Peter Corke,Michael Milford +11 more
TL;DR: A survey of semantics in robotics can be found in this paper, where the authors present a taxonomy of semantics research in or relevant to robotics, split into four broad categories of activity, in which semantics are extracted, used or both.
Posted Content
HistoNet: Predicting size histograms of object instances
TL;DR: This work shows that directly learning histograms of object sizes improves accuracy while using drastically less parameters, and results in an overall improvement in the count and size distribution prediction as compared to state-of-the-art instance segmentation method Mask R-CNN.
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings ArticleDOI
Pyramid Scene Parsing Network
TL;DR: This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
Proceedings Article
Understanding the difficulty of training deep feedforward neural networks
Xavier Glorot,Yoshua Bengio +1 more
TL;DR: The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.
Proceedings ArticleDOI
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts,Mohamed Omran,Sebastian Ramos,Timo Rehfeld,Markus Enzweiler,Rodrigo Benenson,Uwe Franke,Stefan Roth,Bernt Schiele +8 more
TL;DR: This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.