Deep Watershed Transform for Instance Segmentation

Bai, Min; Urtasun, Raquel

doi:10.1109/cvpr.2017.305

Cited by 508 publications

(392 citation statements)

References 25 publications

Supporting

Mentioning

390

Contrasting

Order By: Relevance

“…Finally, the class label for each instance is obtained by voting among all pixels based on semantic segmentation labels. Following DWT [3], small instances are removed and semantic scores from semantic segmentation are used to rank predictions.…”

Section: Cascaded Graph Partitionmentioning

confidence: 99%

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Gao

Shan

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

244

146

View full text Add to dashboard Cite

Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two subtasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits between the two complementary sub-tasks are also unexplored. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on a pixel-pair affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. The affinity pyramid can also be jointly learned with the semantic class labeling and achieve mutual benefits. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine. Unlike previous time-consuming graph partition methods, this module achieves 5× speedup and 9% relative improvement on Average-Precision (AP). Our approach achieves state-of-the-art results on the challenging Cityscapes dataset.

show abstract

Section: Cascaded Graph Partitionmentioning

confidence: 99%

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Gao

Shan

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

244

146

View full text Add to dashboard Cite

show abstract

“…One relies on the R-CNN proposals, which is a bottom-up pipeline that the segmentation results are based on the proposals and then labeled by a classifier [26,27]. The other family relies on semantic segmentation results [28,29] where instance segmentation following semantic segmentation by classifying pixels into different instances. A state-of-the-art method Mask-RCNN [30], built upon object detectors [31], also depends on the proposals but features are shared by classes, box predictors, and mask generators, then all results are collected in parallel.…”

Section: Related Workmentioning

confidence: 99%

Spatio-Temporal Attention Model for Foreground Detection in Cross-Scene Surveillance Videos

Liang

Pan

Sun

et al. 2019

Sensors

View full text Add to dashboard Cite

Foreground detection is an important theme in video surveillance. Conventional background modeling approaches build sophisticated temporal statistical model to detect foreground based on low-level features, while modern semantic/instance segmentation approaches generate high-level foreground annotation, but ignore the temporal relevance among consecutive frames. In this paper, we propose a Spatio-Temporal Attention Model (STAM) for cross-scene foreground detection. To fill the semantic gap between low and high level features, appearance and optical flow features are synthesized by attention modules via the feature learning procedure. Experimental results on CDnet 2014 benchmarks validate it and outperformed many state-of-the-art methods in seven evaluation metrics. With the attention modules and optical flow, its F-measure increased 9% and 6% respectively. The model without any tuning showed its cross-scene generalization on Wallflower and PETS datasets. The processing speed was 10.8 fps with the frame size 256 by 256.

show abstract

“…Resource allocation. Complete computer-vision solutions for cellular image analysis typically require a hybrid of conventional and deep learning methods to achieve a production-ready solution 6,[21][22][23] . We have chosen to separate the conventional and deep learning operations so that they run on different nodes, which allows us to use hardware acceleration for deep learning while ensuring conventional operations are only run on less expensive hardware.…”

Section: Software Architecturementioning

confidence: 99%

“…By changing this rate, we simulated different upload speeds. Our image-analysis routine consisted of performing single-cell segmentation using a deep watershed approach 22,23 , which requires both deep learning and conventional processing steps and reveals the relative impact of different computational operations on inference speed and cost. While we benchmarked scalability using the deep watershed approach, we note that this software can (and has) been adapted to deploy a variety of deep learning methods, including RetinaNet 33 and Mask-RCNN 34 , on biological imaging data.…”

Section: Benchmarkingmentioning

confidence: 99%

DeepCell Kiosk: Scaling deep learning-enabled cellular image analysis with Kubernetes

Bannon

Moen

Schwartz

et al. 2018

Preprint

View full text Add to dashboard Cite

Deep learning is transforming the ability of life scientists to extract information from images. These techniques have better accuracy than conventional approaches and enable previously impossible analyses. As the capability of deep learning methods expands, they are increasingly being applied to large imaging datasets. The computational demands of deep learning present a significant barrier to large-scale image analysis. To meet this challenge, we have developed DeepCell 2.0, a platform for deploying deep learning models on large imaging datasets (>10 5megapixel images) in the cloud. This software enables the turnkey deployment of a Kubernetes cluster on all commonly used operating systems. By using a microservice architecture, our platform matches computational operations with their hardware requirements to reduce operating costs. Further, it scales computational resources to meet demand, drastically reducing the time necessary for analysis of large datasets. A thorough analysis of costs demonstrates that cloud computing is economically competitive for this application. By treating hardware infrastructure as software, this work foreshadows a new generation of software packages for biology in which computational resources are a dynamically allocated resource.

show abstract

Deep Watershed Transform for Instance Segmentation

Cited by 508 publications

References 25 publications

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Spatio-Temporal Attention Model for Foreground Detection in Cross-Scene Surveillance Videos

DeepCell Kiosk: Scaling deep learning-enabled cellular image analysis with Kubernetes

Contact Info

Product

Resources

About