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
Posted Content
EfficientPS: Efficient Panoptic Segmentation
Rohit Mohan,Abhinav Valada +1 more
TL;DR: In this paper, a new semantic head that aggregates fine and contextual features coherently and a new variant of Mask R-CNN as the instance head are proposed for the panoptic segmentation task.
Posted Content
End-to-end Learning Improves Static Object Geo-localization in Monocular Video.
TL;DR: This work presents a system that improves the localization of static objects by jointly-optimizing the components of the system via learning, comprised of networks that perform 5DoF object pose estimation from a single image, association of objects between pairs of frames, and multi-object tracking to produce the final geo-localization of the static objects within the scene.
Proceedings ArticleDOI
Linear colour segmentation revisited
TL;DR: This work proposes a new modification of segmentation algorithm based on a region adjacency graph framework without a pre-segmentation stage and shows that the proposed algorithm modifications lead to qualitative advantages over other model-based segmentation algorithms.
Journal ArticleDOI
Color image segmentation based on SLIC and watershed algorithm
TL;DR: A color image segmentation algorithm based on simple linear iterative clustering (SLIC) and watershed algorithm is proposed to achieve an ideal segmentation effect and can effectively suppress the over-segmentation problem caused by the traditional watershed algorithm.
Book
Human Centric Visual Analysis with Deep Learning
TL;DR: This chapter presents a short review of the foundation of deep learning, i.e., artificial neural network, and introduces some new techniques in deep learning.
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.