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
Proceedings ArticleDOI
TorontoCity: Seeing the World with a Million Eyes
Shenlong Wang,Shenlong Wang,Min Bai,Min Bai,Gellert Mattyus,Gellert Mattyus,Hang Chu,Wenjie Luo,Wenjie Luo,Bin Yang,Bin Yang,Justin Liang,Justin Liang,Joel Cheverie,Sanja Fidler,Raquel Urtasun,Raquel Urtasun +16 more
TL;DR: The TorontoCity benchmark is introduced, which covers the full greater Toronto area with 712.5km2 of land, 8439km of road and around 400, 000 buildings, and a wide variety of tasks including building height estimation, road centerline and curb extraction, building instance segmentation, building contour extraction, semantic labeling and scene type classification are designed.
Proceedings ArticleDOI
Recurrent Pixel Embedding for Instance Grouping
Shu Kong,Charless C. Fowlkes +1 more
TL;DR: A differentiable, end-to-end trainable framework for solving pixel-level grouping problems such as instance segmentation consisting of two novel components, implementing a variant of mean-shift clustering as a recurrent neural network parameterized by kernel bandwidth.
Proceedings ArticleDOI
Improved Road Connectivity by Joint Learning of Orientation and Segmentation
TL;DR: A connectivity task called Orientation Learning, motivated by the human behavior of annotating roads by tracing it at a specific orientation is proposed, and a stacked multi-branch convolutional module is developed to effectively utilize the mutual information between orientation learning and segmentation tasks.
Proceedings ArticleDOI
Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations
TL;DR: In this paper, a new layer and loss are proposed to learn sharp and precise semantic boundaries by explicitly reasoning about annotation noise during training, which can be used with existing learning-based boundary detectors.
Proceedings ArticleDOI
An End-To-End Network for Panoptic Segmentation
TL;DR: Wang et al. as discussed by the authors proposed an end-to-end occlusion aware network (OANet), which can efficiently and effectively predict both the instance and stuff segmentation in a single network.
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.