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
Faster training of Mask R-CNN by focusing on instance boundaries
TL;DR: An auxiliary task to Mask R-CNN, an instance segmentation network, is presented, which leads to faster training of the mask head, and a new prediction head is added, the Edge Agreement Head, which is inspired by the way human annotators perform instance segmentations.
Proceedings ArticleDOI
Learning to Cluster for Proposal-Free Instance Segmentation
TL;DR: Zhang et al. as mentioned in this paper proposed a novel learning objective to train a deep neural network to perform end-to-end image pixel clustering, which is at the intersection of image semantic segmentation and object detection.
Journal ArticleDOI
Establishment of a morphological atlas of the Caenorhabditis elegans embryo using deep-learning-based 4D segmentation.
Jianfeng Cao,Guoye Guan,Vincy Wing Sze Ho,Vincy Wing Sze Ho,Ming Kin Wong,Lu Yan Chan,Chao Tang,Zhongying Zhao,Hong Yan +8 more
TL;DR: An automatic pipeline, CShaper, is reported, which combines automated segmentation of fluorescently labeled membranes with automated cell lineage tracing and generates a time-lapse 3D atlas of cell morphology for the C. elegans embryo from the 4- to 350-cell stages.
Journal ArticleDOI
LaneAF: Robust Multi-Lane Detection With Affinity Fields
TL;DR: In this article, a lane detection method based on binary segmentation masks and per-pixel affinity fields is proposed, which can be used to detect and cluster lanes effectively and robustly.
Journal ArticleDOI
The role of machine learning to boost the bioenergy and biofuels conversion.
TL;DR: In this paper, the strengths and limitations of ML in bioenergy systems are comprehensively analysed and highlighted the capabilities and potential of advanced ML methods when encountering multifarious tasks in the future prospects to advance a new generation of bioenergy and biofuels conversion technologies.
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.