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
DeepSignals: Predicting Intent of Drivers Through Visual Signals
TL;DR: This paper proposes to detect turn signals and emergency flashers in video sequences by using a deep neural network that reasons about both spatial and temporal information.
Book ChapterDOI
PatchPerPix for Instance Segmentation
TL;DR: In this article, a non-iterative method is proposed for instance segmentation that can handle sophisticated object shapes which span large parts of an image and form dense object clusters with crossovers.
Journal ArticleDOI
Instance segmentation of biological images using graph convolutional network
TL;DR: Zhang et al. as discussed by the authors proposed a graph-guided feature fusion module for instance segmentation in biological images, which combines fine deep features and coarse shallow features to learn the affinity matrix, and then uses graph convolutional network to guide the network to learn object-level local features.
Proceedings ArticleDOI
Integrated Learning and Feature Selection for Deep Neural Networks in Multispectral Images
Anthony Ortiz,Alonso Granados,Olac Fuentes,Christopher Kiekintveld,Dalton Rosario,Zachary Bell +5 more
TL;DR: It is shown that Integrated Learning and Feature Selection (ILFS) significantly improves performance on neural networks for multispectral imagery applications and also evaluates the proposed methodology as a potential defense against adversarial examples, which are malicious inputs carefully designed to fool a machine learning system.
Journal ArticleDOI
Panoptic Feature Fusion Net: A Novel Instance Segmentation Paradigm for Biomedical and Biological Images.
TL;DR: Panoptic Feature Fusion Networks (PFFNet) as discussed by the authors unifies the semantic and instance features in this work by incorporating residual attention feature fusion mechanism to incorporate the instance prediction with the semantic features, in order to facilitate the semantic contextual information learning in the instance branch.
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.