Course Recap and What’s Next?

Slides:



Advertisements
Similar presentations
Face Recognition: A Convolutional Neural Network Approach
Advertisements

Classification spotlights
ImageNet Classification with Deep Convolutional Neural Networks
Artificial Neural Networks
Spatial Pyramid Pooling in Deep Convolutional
From R-CNN to Fast R-CNN
Deep face recognition Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman.
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
Fully Convolutional Networks for Semantic Segmentation
Unsupervised Visual Representation Learning by Context Prediction
Object Recognizing. Deep Learning Success in 2012 DeepNet and speech processing.
Rich feature hierarchies for accurate object detection and semantic segmentation 2014 IEEE Conference on Computer Vision and Pattern Recognition Ross Girshick,
Deep Residual Learning for Image Recognition
Introduction to Convolutional Neural Networks
Lecture 3b: CNN: Advanced Layers
Learning to Answer Questions from Image Using Convolutional Neural Network Lin Ma, Zhengdong Lu, and Hang Li Huawei Noah’s Ark Lab, Hong Kong
Convolutional Neural Networks
Recent developments in object detection
CNN architectures Mostly linear structure
Deep Residual Learning for Image Recognition
Demo.
Faster R-CNN – Concepts
Convolutional Neural Network
Machine Learning for Big Data
Object Detection based on Segment Masks
DeepCount Mark Lenson.
The Problem: Classification
Matt Gormley Lecture 16 October 24, 2016
Deep Learning Hung-yi Lee 李宏毅.
Regularizing Face Verification Nets To Discrete-Valued Pain Regression
Inception and Residual Architecture in Deep Convolutional Networks
Structured Predictions with Deep Learning
Training Techniques for Deep Neural Networks
Machine Learning: The Connectionist
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Adversarially Tuned Scene Generation
ECE 599/692 – Deep Learning Lecture 6 – CNN: The Variants
State-of-the-art face recognition systems
Zan Gao, Deyu Wang, Xiangnan He, Hua Zhang
Computer Vision James Hays
Introduction to Neural Networks
Neural network systems
Image Classification.
Deep Learning Tutorial
Object Detection + Deep Learning
Very Deep Convolutional Networks for Large-Scale Image Recognition
Smart Robots, Drones, IoT
CornerNet: Detecting Objects as Paired Keypoints
A Proposal Defense On Deep Residual Network For Face Recognition Presented By SAGAR MISHRA MECE
Faster R-CNN By Anthony Martinez.
GAN Applications.
Lecture: Deep Convolutional Neural Networks
Deep Learning for Non-Linear Control
Visualizing CNNs and Deeper Deep Architectures
Papers 15/08.
Machine Learning – Neural Networks David Fenyő
RCNN, Fast-RCNN, Faster-RCNN
Speakers: Luo Mai, Jingqing Zhang
Heterogeneous convolutional neural networks for visual recognition
Face Recognition: A Convolutional Neural Network Approach
Abnormally Detection
Human-object interaction
CS295: Modern Systems: Application Case Study Neural Network Accelerator Sang-Woo Jun Spring 2019 Many slides adapted from Hyoukjun Kwon‘s Gatech “Designing.
Recent Advances in Neural Architecture Search
Debasis Bhattacharya, JD, DBA University of Hawaii Maui College
End-to-End Facial Alignment and Recognition
CRCV REU 2019 Kara Schatz.
Prabhas Chongstitvatana Chulalongkorn University
CRCV REU 2019 Aaron Honculada.
ICLR, 2019 Jiahe Li
Presentation transcript:

Course Recap and What’s Next?

Course Recap What did we learn this semester?

Image Processing and Manipulation Image Processing – Brightness, Saturation, Color Spaces Image Convolution / Filtering: Blurring, Sharpness, Noise Removal Image Gradients / Sobel Operators / Features

Basic Machine Learning and Image Classification Softmax Classifier / Linear Classifiers in General Stochastic Gradient Descent (SGD) Momentum, Regularization, Choosing Hyperparameters

Deep Learning Multi-layer Perceptron / Neural Networks The backpropagation algorithm Implementing our own Deep Learning Toolkit / Library

Deep Learning for Visual Recognition: Classification Alexnet, VGG Networks. Residual Connections, Resnets Google Net, Inception Nets

Deep Learning for Visual Recognition: Detection / Segmentation Convolutional Neural Networks (CNNs) Object Detection: RCNN, Fast-RCNN, Faster-RCNN, SSD, YOLO, SNIPER Image Segmentation: Deconvolutions, Fully Convolutional Networks, U-Nets.

Deep Learning for Visual Recognition: Synthesis Generating Images: Generative Adversarial Networks (GANs), Variational Auto-Encoder (VAEs)

Deep Learning for Visual Recognition: Other Tasks Human Pose Estimation: Hourglass Networks Matching: Siamese Networks, Triplet Losses

What else is coming? Image Classification Models have almost peaked on Imagenet Model search: How to find model architectures automatically!

What else is coming? Image Classification Models have almost peaked on Imagenet Model search: How to find model architectures automatically! These models are as fast as Resnet models but ~2% more accurate (79% vs 77%)

What else is coming? Object Detection CornerNets, CenterNets “CornerNet: Detecting Objects as Paired Keypoints” by Hei Law, and Jia Deng ECCV 2018

What else is coming? Object Detection CornerNets, CenterNets “CornerNet: Detecting Objects as Paired Keypoints” by Hei Law, and Jia Deng ECCV 2018

What else is coming? Object Detection CornerNets, CenterNets *CenterNet: Keypoint Triplets for Object Detection by Kaiwen Duan et al. April 17, 2019 arXiv Objects as Points. Xingyi Zhou, Dequan Wang, Philipp Krähenbühl. April 2019.

Interpretable Deep Learning This Looks Like That: Deep Learning for Interpretable Image Recognition. Chen et al 2018.

Here at UVA In Submission

Here at UVA How to learn Interpretable and Robust models? How to learn models that do not need as much training data? How to learn faster models? e.g. XNOR-Nets How to better represent multimodal features? (images + text) How to build compositional models for unusual images?

Thanks and All the Best!