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
Affinity Derivation and Graph Merge for Instance Segmentation
TL;DR: This work presents an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to the same instance, which uses two neural networks with similar structures to cluster pixels into instances.
Proceedings ArticleDOI
Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
Wei-Chiu Ma,Raquel Urtasun,Ignacio Tartavull,Ioan Andrei Barsan,Shenlong Wang,Min Bai,Gellert Mattyus,Namdar Homayounfar,Shrinidhi Kowshika Lakshmikanth,Andrei Pokrovsky +9 more
TL;DR: A novel semantic localization algorithm that exploits multiple sensors and has precision on the order of a few centimeters is proposed that does not require detailed knowledge about the appearance of the world, and requires orders of magnitude less storage than maps utilized by traditional geometry- and LiDAR intensity-based localizers.
Proceedings ArticleDOI
Mask Encoding for Single Shot Instance Segmentation
TL;DR: Instead of predicting the two-dimensional mask directly, MEInst distills it into a compact and fixed-dimensional representation vector, which allows the instance segmentation task to be incorporated into one-stage bounding-box detectors and results in a simple yet efficient instance segmentations framework.
Journal ArticleDOI
TextMountain: Accurate scene text detection via instance segmentation
Yixing Zhu,Jun Du +1 more
TL;DR: TextMountain this article predicts text center-border probability (TCBP) and text center direction (TCD) to separate text instances which cannot be easily achieved using semantic segmentation map and its rising direction can plan a road to top for each pixel on mountain foot at the group stage.
Journal ArticleDOI
Scene Understanding With Automotive Radar
TL;DR: This work presents a complete pipeline to obtain semantic information for each target measured by a network of radar sensors and develops a new set of layers for radar grid maps which are beneficial for semantic segmentation tasks.
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.