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
Journal ArticleDOI
DeepFlux for Skeleton Detection in the Wild
Yongchao Xu,Yukang Wang,Stavros Tsogkas,Stavros Tsogkas,Jianqiang Wan,Xiang Bai,Sven Dickinson,Sven Dickinson,Kaleem Siddiqi +8 more
TL;DR: Wang et al. as discussed by the authors used a convolutional neural network to predict a two-dimensional vector field encoding the flux representation, which captures the position of skeletal pixels relative to semantically meaningful entities (e.g., image points in spatial context, and hence the implied object boundaries).
Journal ArticleDOI
Semantic Cameras for 360-Degree Environment Perception in Automated Urban Driving
TL;DR: The European UP-Drive project as mentioned in this paper developed a prototype electrical vehicle equipped with cameras and LiDARs sensors that is capable to autonomously drive around the city and find available parking spots.
Proceedings ArticleDOI
DeepSignals: Predicting Intent of Drivers Through Visual Signals
TL;DR: Turn signals and emergency flashers communicate such intentions, providing seconds of potentially critical reaction time in self-driving cars as discussed by the authors, and the authors propose to detect these signals in video sequences by using a deep neural network that reasons about both spatial and temporal information.
Posted Content
Distance to Center of Mass Encoding for Instance Segmentation
Thomio Watanabe,Denis F. Wolf +1 more
TL;DR: Distance to Center of Mass Encoding (DCME) as discussed by the authors is a mathematical representation of instances that any deep semantic segmentation model can learn and generalize, where each individual instance is represented by a center of mass and a field of vectors pointing to it.
Journal ArticleDOI
Attention aware cross faster RCNN model and simulation
TL;DR: The experimental results show that the Cross Faster R-CNN model, which introduces the cross-connected layer and attention mechanism, has no major changes in detection speed, and the accuracy is significantly improved.
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.