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
Incorporating Non-local and Task-specific Features for Instance Segmentation
TL;DR: A novel instance segmentation model is proposed, which improves the instances segmentation by considering two aspects, one is a new non-local features module to recover detailed information that is lost in the deep convolutional operations and the other is to introduce attention mechanism to generate specific features adaptive to each task.
Proceedings ArticleDOI
Deep Counting Model Extensions with Segmentation for Person Detection
TL;DR: This paper focuses on the problem of detecting each instance of a specific category of objects, specifically persons, based on a deep counting model that outperforms other methods on the CUHK08 dataset with an Average Miss Rate (AMR) of 14% and on the PETS09 datasets with an AMR of 41%.
Journal ArticleDOI
HEVC based tampered video database development for forensic investigation
Journal ArticleDOI
A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation
TL;DR: In this paper, a multi-task learning (MTL)-based regularization framework for cardiac MR image segmentation is proposed. But the proposed regularization method is not suitable for the task of binary and multi-class segmentation.
Proceedings ArticleDOI
An Ensemble Learning and Slice Fusion Strategy for Three-Dimensional Nuclei Instance Segmentation
TL;DR: Li et al. as mentioned in this paper proposed an ensemble learning and slice fusion strategy for 3D nuclei instance segmentation that uses different object detectors to generate nuclei segmentation masks for each 2D slice of a volume and propose a 2D ensemble fusion and 2D to 3D slice fusion to merge these 2D masks into a 3D segmentation mask.
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.