paper-with-me

홈 › Papers

Object Detection via a Multi-Region and Semantic Segmentation-Aware CNN Model

2015-12-01 · ICCV 2015 12 · Spyros Gidaris, Nikos Komodakis

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates between scoring a box proposal and refining its location with a deep CNN regression model. Thanks to the efficient use of our modules, we detect objects with very high localization accuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.

📄 PDF Abstract BibTeX

Code (1)

gidariss/mrcnn-object-detection 공식 구현

Tasks

Objectobject-detectionObject DetectionObject LocalizationSemantic Segmentation

Similar Papers 제목 키워드 기반

Semantic Object Segmentation via Detection in Weakly Labeled Video

2015-06-01 · CVPR 2015 6 · Yu Zhang, Xiaowu Chen, Jia Li, Chen Wang 외

Semantic object segmentation in video is an important step for large-scale multimedia analysis. In many cases, however, semantic objects are only tagged at video-level, making them difficult to be located and segmented. …

Objectobject-detectionObject DetectionSegmentation+1

Object detection via a multi-region & semantic segmentation-aware CNN model

2015-05-07 · Spyros Gidaris, Nikos Komodakis

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing…

Objectobject-detectionObject DetectionObject Localization+2

MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features

2017-12-13 · CVPR 2018 6 · Liang-Chieh Chen, Alexander Hermans, George Papandreou, Florian Schroff 외

In this work, we tackle the problem of instance segmentation, the task of simultaneously solving object detection and semantic segmentation. Towards this goal, we present a model, called MaskLab, which produces three out…

Instance SegmentationObjectobject-detectionObject Detection+3

Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

2017-09-11 · Yuchen Dai, Zheng Huang, Yuting Gao, Youxuan Xu 외

In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective. We present Fused Text Segmentation Networks, which combine multi-lev…

Multi-Oriented Scene Text Detectionobject-detectionObject DetectionRegion Proposal+5

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

2017-01-17 · Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Pablo Arbeláez, Luc van Gool

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computational…

Boundary DetectionContour Detectionimage-classificationImage Classification+6