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
Gabor Layers Enhance Network Robustness
Juan C. Pérez,Motasem Alfarra,Guillaume Jeanneret,Adel Bibi,Ali Thabet,Bernard Ghanem,Pablo Arbeláez +6 more
TL;DR: It is observed that architectures enhanced with Gabor layers gain a consistent boost in robustness over regular models and preserve high generalizing test performance, even though these layers come at a negligible increase in the number of parameters.
Journal ArticleDOI
APANet: Auto-Path Aggregation for Future Instance Segmentation Prediction.
TL;DR: Zhang et al. as mentioned in this paper proposed an adaptive aggregation approach called Auto-Path Aggregation Network (APANet), where the spatio-temporal contextual information obtained in the features of each individual level is selectively aggregated using the developed ''auto-path'' to connect each pair of features extracted at different pyramid levels for task-specific hierarchical contextual information aggregation.
Posted ContentDOI
Development of Convolutional Neural Network Based Instance Segmentation Algorithm to Acquire Quantitative Criteria of Mouse Development
TL;DR: In this paper, the authors proposed a method based on Convolutional Neural Network (CNN) to perform nuclear segmentation of three-dimensional fluorescence microscopic images for early-stage mouse embryos.
Journal ArticleDOI
Deep learning-based segmentation for disease identification
Olfa Mzoughi,Itheri Yahiaoui +1 more
TL;DR: In this article , the authors proposed a new perspective to handle the problem with two main differences: first, while most approach aims to identify simultaneously a pair of species-disease, they propose to identify diseases independently of leaf species.
Journal ArticleDOI
SCG: Saliency and Contour Guided Salient Instance Segmentation
TL;DR: Zhang et al. as mentioned in this paper proposed Mask R-CNN to leverage complementary saliency and contour information for salient instance segmentation, which achieved state-of-the-art performance on the ILSO dataset.
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.