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
Constructing 3D Models of Rigid Objects from Satellite Images with High Spatial Resolution Using Convolutional Neural Networks
TL;DR: In this paper, a way of constructing 3D models of rigid objects from one satellite image is described based on the use of two convolutional neural networks which sequentially process high-resolution satellite images.
Journal ArticleDOI
Semantic segmentation-assisted instance feature fusion for multi-level 3D part instance segmentation
TL;DR: Zhang et al. as discussed by the authors exploited semantic segmentation to fuse nonlocal instance features, such as center prediction, and further enhances the fusion scheme in a multi-and cross-level way.
Proceedings ArticleDOI
A Superpixel-based Water Scene Segmentation Method by Sea-sky-line and Shoreline Detection
TL;DR: In this paper, a multiscale morphological gradient reconstruction (MMGR) and watershed algorithm were used to segment the water scene more accurately. And then the superpixels were aggregated by fuzzy c-means (FCM) to get water scene segmentation.
Journal ArticleDOI
Bridging the Gap Between Semantic Segmentation and Instance Segmentation
TL;DR: Sem2Ins as discussed by the authors proposes a real-time model for instance segmentation, which effectively generates instance boundaries according to a semantic segmentation by leveraging conditional generative adversarial networks (cGANs) coupled with deep supervision and a weighted fusion layer.
Book ChapterDOI
Adversarially Robust Panoptic Segmentation (ARPaS) Benchmark
TL;DR: In this article , the Adversarially Robust Panoptic Segmentation (ARPaS) benchmark is proposed to assess the general robustness of panoptic segmentation techniques.
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.