Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection

Published in

IEEE Workshop/Winter Conference on Applications...(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

A novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification that achieves state of-the-art performance on both detection and pose estimation on commonly used benchmarks are introduced.

Abstract

In Convolutional Neural Network (CNN)-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve state of-the-art performance on both detection and pose estimation on commonly used benchmarks.

Authors

S. Savarese

31 papers

Yu Xiang

8 papers

Yuanqing Lin

2 papers

References43 items

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

Monocular 3D Object Detection for Autonomous Driving

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

3D Object Proposals for Accurate Object Class Detection

Deep Learning Strong Parts for Pedestrian Detection

Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection

Published in

IEEE Workshop/Winter Conference on Applications...(2016)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

S. Savarese

31 papers

Yu Xiang

8 papers

Yuanqing Lin

2 papers

References43 items

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

Monocular 3D Object Detection for Autonomous Driving

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

3D Object Proposals for Accurate Object Class Detection

Deep Learning Strong Parts for Pedestrian Detection

Wongun Choi

2 papers

Multi-View and 3D Deformable Part Models

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Data-driven 3D Voxel Patterns for object category recognition

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

Learning to Detect Vehicles by Clustering Appearance Patterns

Filtered channel features for pedestrian detection

Viewpoints and keypoints

Going deeper with convolutions

Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model

Edge Boxes: Locating Object Proposals from Edges

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Fast Feature Pyramids for Object Detection

Multiscale Combinatorial Grouping

Enriching Visual Knowledge Bases via Object Discovery and Segmentation

Learning Everything about Anything: Webly-Supervised Visual Concept Learning

Caffe: Convolutional Architecture for Fast Feature Embedding

Beyond PASCAL: A benchmark for 3D object detection in the wild

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Regionlets for Generic Object Detection

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Occlusion Patterns for Object Class Detection

Selective Search for Object Recognition

ImageNet classification with deep convolutional neural networks

Are we ready for autonomous driving? The KITTI vision benchmark suite

How Important Are "Deformable Parts" in the Deformable Parts Model?

Ensemble of exemplar-SVMs for object detection and beyond

Discriminative Mixture-of-Templates for Viewpoint Classification

Object Detection with Discriminatively Trained Part Based Models

Clustering by Passing Messages Between Data Points

Robust Real-Time Face Detection

Kitti object detection benchmark. http://www.cvlibs.net/datasets/kitti/eval object.php Accessed: 2016-03-13

Car Detection and Orientation Estimation on KITTI Object Detection (AP) Object Detection and Orientation estimation (AOS) Method Easy Moderate Hard Easy Moderate Hard ACF

TL;DR

Abstract

Authors

References43 items

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

Monocular 3D Object Detection for Autonomous Driving

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

3D Object Proposals for Accurate Object Class Detection

Deep Learning Strong Parts for Pedestrian Detection

TL;DR

Abstract

Authors

References43 items

A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

Monocular 3D Object Detection for Autonomous Driving

Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

3D Object Proposals for Accurate Object Class Detection

Deep Learning Strong Parts for Pedestrian Detection

Multi-View and 3D Deformable Part Models

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Data-driven 3D Voxel Patterns for object category recognition

Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

Fast R-CNN

Learning to Detect Vehicles by Clustering Appearance Patterns

Filtered channel features for pedestrian detection

Viewpoints and keypoints

Going deeper with convolutions

Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model

Edge Boxes: Locating Object Proposals from Edges

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Fast Feature Pyramids for Object Detection

Multiscale Combinatorial Grouping

Enriching Visual Knowledge Bases via Object Discovery and Segmentation

Learning Everything about Anything: Webly-Supervised Visual Concept Learning

Caffe: Convolutional Architecture for Fast Feature Embedding

Beyond PASCAL: A benchmark for 3D object detection in the wild

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Regionlets for Generic Object Detection

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Occlusion Patterns for Object Class Detection

Selective Search for Object Recognition

ImageNet classification with deep convolutional neural networks

Are we ready for autonomous driving? The KITTI vision benchmark suite

How Important Are "Deformable Parts" in the Deformable Parts Model?

Ensemble of exemplar-SVMs for object detection and beyond

Discriminative Mixture-of-Templates for Viewpoint Classification

Object Detection with Discriminatively Trained Part Based Models

Clustering by Passing Messages Between Data Points

Robust Real-Time Face Detection

Kitti object detection benchmark. http://www.cvlibs.net/datasets/kitti/eval object.php Accessed: 2016-03-13

Car Detection and Orientation Estimation on KITTI Object Detection (AP) Object Detection and Orientation estimation (AOS) Method Easy Moderate Hard Easy Moderate Hard ACF

The Pascal Visual Object Classes Challenge 2006 ( VOC 2006 ) Results

The PASCAL Visual Object Classes Challenge

Edinburgh Research Explorer The PASCAL Visual Object Classes (VOC) Challenge

Ur- tasun. Kitti object detection benchmark

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names