A MultiPath Network for Object Detection

Zagoruyko, Sergey; Lerer, Adam; Lin, Tsung-Yi; Pinheiro, Pedro O.; Gross, Sam; Chintala, Soumith; Dollár, Piotr

doi:10.48550/arxiv.1604.02135

Cited by 32 publications

(44 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One recent study has used a pixels-to-pixels type CNN to process raw STORM microscopy data into super-resolution images [39]. The potential for this technology to address outstanding bio-imaging problems is becoming clear, particularly for image segmentation, which is an active research area in machine learning [19,40,41,42,43,44,45].…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

Newby

Schaefer

Lee

et al. 2018

Proc. Natl. Acad. Sci. U.S.A.

163

120

View full text Add to dashboard Cite

Particle tracking is a powerful biophysical tool that requires conversion of large video files into position time series, i.e. traces of the species of interest for data analysis. Current tracking methods, based on a limited set of input parameters to identify bright objects, are ill-equipped to handle the spectrum of spatiotemporal heterogeneity and poor signal-to-noise ratios typically presented by submicron species in complex biological environments. Extensive user involvement is frequently necessary to optimize and execute tracking methods, which is not only inefficient but introduces user bias. To develop a fully automated tracking method, we developed a convolutional neural network for particle localization from image data, comprised of over 6,000 parameters, and employed machine learning techniques to train the network on a diverse portfolio of video conditions. The neural network tracker provides unprecedented automation and accuracy, with exceptionally low false positive and false negative rates on both 2D and 3D simulated videos and 2D experimental videos of difficult-to-track species. Significance StatementThe increasing availability of powerful light microscopes capable of collecting terabytes of high-resolution 2D and 3D videos in a single day has created a great demand for automated image analysis tools. Tracking the movement of nanometer scale particles (e.g., virus, proteins, synthetic drug particles) is critical for understanding how pathogens breach mucosal barriers and for the design of new drug therapies. Our advancement is to use an artificial neural network that provides, first and foremost, substantially improved automation. Additionally, our method improves accuracy compared to current methods and reproducibility across users and labs.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

Newby

Schaefer

Lee

et al. 2018

Proc. Natl. Acad. Sci. U.S.A.

163

120

View full text Add to dashboard Cite

show abstract

“…Since appearing in 2015, Faster R-CNN has been par-ticularly influential, and has led to a number of follow-up works [2,35,34,46,13,5,19,45,24,47] (including SSD and R-FCN). Notably, half of the submissions to the COCO object detection server as of November 2016 are reported to be based on the Faster R-CNN system in some way.…”

Section: Faster R-cnnmentioning

confidence: 99%

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Huang

Rathod

Sun

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

2,112

1,379

View full text Add to dashboard Cite

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-toapples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [31], R-FCN [6] and SSD [26] systems, which we view as "meta-architectures" and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.

show abstract

“…images include [24]- [27]. While there has been significant progress, at present these methods lack the accuracy and the speed to be usable in our online framework.…”

Section: B Object Detection and Semantic Segmentationmentioning

confidence: 99%

“…Therefore, a method to localize and recognize different object instances in an image is needed. Although there is considerable progress on instance level semantic segmentation [24]- [28], these works are not sufficiently fast for our semantic mapping framework. For example, DeepMask [28] takes about 1.6s per image.…”

Section: B Object Detection For Semantic Mappingmentioning

confidence: 99%

Meaningful maps with object-oriented semantic mapping

Sünderhauf

Pham

Latif

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

195

136

View full text Add to dashboard Cite

Fig. 1: We demonstrate object-oriented semantic mapping using RGB-D data that scales from small desktop environments (left) to offices (middle) and whole labs (right). The pictures show 3D map structures with objects colored according to their semantic class. We do not merely project semantic labels for individual 3D points, but rather maintain objects as the central entity of the map, freeing it from the requirement for a-priori 3D object models in [1]. To achieve this, our system creates and extends 3D object models while continuously mapping the environment. Object detection and classification is performed using a Convolutional Network, while an unsupervised 3D segmentation algorithm assigns a segment of 3D points to every object detection. These segmented object detections are then either fused with existing objects, or added as a new object to the map. ORB-SLAM2 provides a global SLAM solution that enables us to reconstruct a 3D model of the environment that contains both non-object structure and objects of various types.Abstract-For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic mapping. In this paper we address the problem of building environmental maps that include both semantically meaningful, object-level entities and point-or mesh-based geometrical representations. We simultaneously build geometric point cloud models of previously unseen instances of known object classes and create a map that contains these object models as central entities. Our system leverages sparse, feature-based RGB-D SLAM, image-based deep-learning object detection and 3D unsupervised segmentation.

show abstract

A MultiPath Network for Object Detection

Cited by 32 publications

References 0 publications

Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Meaningful maps with object-oriented semantic mapping

Contact Info

Product

Resources

About