Jiahe Li 2019.03.04.

Slides:



Advertisements
Similar presentations
Object-centric spatial pooling for image classification Olga Russakovsky, Yuanqing Lin, Kai Yu, Li Fei-Fei ECCV 2012.
Advertisements

Large-Scale Object Recognition with Weak Supervision
R-CNN By Zhang Liliang.
DeeperVision and DeepInsight Solutions
Spatial Pyramid Pooling in Deep Convolutional
From R-CNN to Fast R-CNN
Generic object detection with deformable part-based models
Detection, Segmentation and Fine-grained Localization
BING: Binarized Normed Gradients for Objectness Estimation at 300fps
Object detection, deep learning, and R-CNNs
Fully Convolutional Networks for Semantic Segmentation
Face Alignment at 3000fps via Regressing Local Binary Features CVPR14 Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun Presented by Sung Sil Kim.
Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation.
Feedforward semantic segmentation with zoom-out features
Describing People: A Poselet-Based Approach to Attribute Classification.
Unsupervised Visual Representation Learning by Context Prediction
Cascade Region Regression for Robust Object Detection
Rich feature hierarchies for accurate object detection and semantic segmentation 2014 IEEE Conference on Computer Vision and Pattern Recognition Ross Girshick,
Spatial Localization and Detection
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition arXiv: v4 [cs.CV(CVPR)] 23 Apr 2015 Kaiming He, Xiangyu Zhang, Shaoqing.
Facial Smile Detection Based on Deep Learning Features Authors: Kaihao Zhang, Yongzhen Huang, Hong Wu and Liang Wang Center for Research on Intelligent.
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Recent developments in object detection
Deep Residual Learning for Image Recognition
CS 4501: Introduction to Computer Vision Object Localization, Detection, Semantic Segmentation Connelly Barnes Some slides from Fei-Fei Li / Andrej Karpathy.
CNN-RNN: A Unified Framework for Multi-label Image Classification
Demo.
Faster R-CNN – Concepts
What Convnets Make for Image Captioning?
Object Detection based on Segment Masks
Object detection with deformable part-based models
YOLO9000:Better, Faster, Stronger
CNN Demo LIU Pengpeng.
Week 6 Cecilia La Place.
Lecture 5 Smaller Network: CNN
Efficient Deep Model for Monocular Road Segmentation
CS6890 Deep Learning Weizhen Cai
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Adri`a Recasens, Aditya Khosla, Carl Vondrick, Antonio Torralba
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Object detection.
A Convolutional Neural Network Cascade For Face Detection
Bird-species Recognition Using Convolutional Neural Network
Neural network systems
Paper Presentation Aryeh Zapinsky
RGB-D Image for Scene Recognition by Jiaqi Guo
Object Detection + Deep Learning
On-going research on Object Detection *Some modification after seminar
Hairong Qi, Gonzalez Family Professor
Tina Jiang. , Vivek Natarajan. , Xinlei Chen
Faster R-CNN By Anthony Martinez.
On Convolutional Neural Network
Outline Background Motivation Proposed Model Experimental Results
Object Tracking: Comparison of
RCNN, Fast-RCNN, Faster-RCNN
Learning Object Context for Dense Captioning
Category-Sensitive Question Routing in Community Question Answering
Neural Network Pipeline CONTACT & ACKNOWLEDGEMENTS
Department of Computer Science Ben-Gurion University of the Negev
Human-object interaction
Deep Object Co-Segmentation
Experience on Crowd-Human Challenge
Semantic Segmentation
Object Detection Implementations
End-to-End Facial Alignment and Recognition
YOLO-based Object Detection on ARM Mali GPU
Eliminating Background-Bias for Robust Person Re-identification
Week 7: Moving Target Detection Using Infrared Sensors
Jiahe Li
CVPR2019 Jiahe Li SiamRPN introduces the region proposal network after the Siamese network and performs joint classification and regression.
Presentation transcript:

Jiahe Li 2019.03.04

Outlines Related Work Framework Datasets Experiments Conclusions

Regions with CNN features

Faster RCNN - RPN

R-FCN Framework

Loss Function

Position-sensitive RoI pooling

Datasets & Metrics PASCAL VOC MS COCO dataset 20 object categories VOC 2007 and VOC 2012 MS COCO dataset 80 object categories 80k train set, 40k val set, and 20k test-dev set mean Average Precision (mAP)

Fully Convolutional Strategies

Faster R-CNN vs R-FCN

Result on PASCAL VOC

Result on MS COCO

Results

Conclusions Region-based Fully Convolutional Networks A simple but accurate and efficient framework