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
Joint multi-task cascade for instance segmentation
TL;DR: A joint multi-tasking cascade structure is proposed, which is not simply to cascade the two tasks of detection and segmentation, but to unitedly put them into multi-stage processing, and especially to integrate the information at different stages of the mask branch.
Posted Content
PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding.
TL;DR: This work proposes a simple, fast, and flexible framework to generate simultaneously semantic and instance masks for panoptic segmentation and introduces position-sensitive embedding for instance grouping by accounting for both object's appearance and its spatial location.
Journal ArticleDOI
OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers
TL;DR: Lallen et al. as mentioned in this paper proposed OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS), which is based on two key designs: a location-sensing transformer (LST) and a coarse-to-fine fusion (CFF) to merge diverse context information from the LST encoder and CNN backbone.
Proceedings ArticleDOI
Contextual Image Parsing via Panoptic Segment Sorting
TL;DR: This work takes the metric learning perspective of SegSort but extends it non-trivially to panoptic segmentation, as it must merge segments into proper instances and handle instances of various scales.
Journal ArticleDOI
Instance-Level Microtubule Tracking
TL;DR: In this paper, a new method of instance-level microtubule (MT) tracking in time-lapse image series using recurrent attention is proposed, where segmentation results from successive frames are used to assign correspondences among MTs.
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.