Object Classification through Deconvolutional Neural Networks

Slides:



Advertisements
Similar presentations
A brief review of non-neural-network approaches to deep learning
Advertisements

Lecture 5: CNN: Regularization
ImageNet Classification with Deep Convolutional Neural Networks
Lecture 14 – Neural Networks
Convolutional Neural Networks for Image Processing with Applications in Mobile Robotics By, Sruthi Moola.
Radial Basis Function Networks:
Feedforward semantic segmentation with zoom-out features
ImageNet Classification with Deep Convolutional Neural Networks Presenter: Weicong Chen.
Object Recognizing. Deep Learning Success in 2012 DeepNet and speech processing.
Lecture 3b: CNN: Advanced Layers
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Lecture 3a Analysis of training of NN
Big data classification using neural network
Demo.
Faster R-CNN – Concepts
The Relationship between Deep Learning and Brain Function
CS 6501: 3D Reconstruction and Understanding Convolutional Neural Networks Connelly Barnes.
Environment Generation with GANs
Summary of “Efficient Deep Learning for Stereo Matching”
Compact Bilinear Pooling
Object Classification through Deconvolutional Neural Networks
Data Mining, Neural Network and Genetic Programming
ECE 5424: Introduction to Machine Learning
Computer Science and Engineering, Seoul National University
Object Detection with Bootstrapping
ECE 6504 Deep Learning for Perception
Training Techniques for Deep Neural Networks
Convolutional Networks
Urban Sound Classification with a Convolution Neural Network
CS6890 Deep Learning Weizhen Cai
Machine Learning: The Connectionist
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Non-linear classifiers Neural networks
Dynamic Routing Using Inter Capsule Routing Protocol Between Capsules
Network In Network Authors: Min Lin, Qiang Chen, Shuicheng Yan
Introduction to Convolutional Neural Network (CNN/ConvNET)-insights from amateur George (Tian Zhou)
Computer Vision James Hays
Introduction to Neural Networks
Image Classification.
CSC 578 Neural Networks and Deep Learning
Two-Stream Convolutional Networks for Action Recognition in Videos
Counting in Dense Crowds using Deep Learning
Convolutional Neural Networks
Deep learning Introduction Classes of Deep Learning Networks
Object Classification through Deconvolutional Neural Networks
Smart Robots, Drones, IoT
Object Classes Most recent work is at the object level We perceive the world in terms of objects, belonging to different classes. What are the differences.
CSC 578 Neural Networks and Deep Learning
A Proposal Defense On Deep Residual Network For Face Recognition Presented By SAGAR MISHRA MECE
LECTURE 35: Introduction to EEG Processing
Lecture: Deep Convolutional Neural Networks
LECTURE 33: Alternative OPTIMIZERS
Object Classification through Deconvolutional Neural Networks
Forward and Backward Max Pooling
Analysis of Trained CNN (Receptive Field & Weights of Network)
Convolutional Neural Networks
Mihir Patel and Nikhil Sardana
ImageNet Classification with Deep Convolutional Neural Networks
Heterogeneous convolutional neural networks for visual recognition
Face Recognition: A Convolutional Neural Network Approach
CSC 578 Neural Networks and Deep Learning
CIS 519 Recitation 11/15/18.
Department of Computer Science Ben-Gurion University of the Negev
Automatic Handwriting Generation
Deep Object Co-Segmentation
Image recognition.
CSC 578 Neural Networks and Deep Learning
CSC 578 Neural Networks and Deep Learning
Week 7 Presentation Ngoc Ta Aidean Sharghi
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Presentation transcript:

Object Classification through Deconvolutional Neural Networks Student: Carlos Rubiano Mentor: Oliver Nina

Network in Network Model different from typical CNN that aims to enhance discriminability for local patches in receptive field Traditional CNN stacks convolutional and pooling layers and then combines layers in fully connected layer at end Loss of spatial information Over fitting can occur

Network in Network NIN’s model: Passed through multilayer perceptron and then through stacked ‘mlp’ convolutional layers that have composing elements which represent micro networks Essentially NIN’s micro networks seperates input image into segments and classifies them individually whereas traditional CNN will look at different level of features in each convolutional layer and then combine the features at the end Rather than using fully connected layer, NIN uses a global average pooling layer which natively prevents overfitting arxiv.org/pdf/1312.4400v3.pdf

Rectifier Linear Unit Standard way to model neuron’s output: f(x) = tanh(x) However very slow Hinton and Nair: f(x) = max(0, x) Maxout:

Feature Map Calculations

UT-Interaction Dataset Dataset with 2 sets of 6 classes with 10 sequences for each class (total of 120 sequences) Extracted frames from segments Resized images to fit our network Calculated the Optical flow Results Imagenet: 59%, Current system: 64%

What’s Next? MBH descriptor seperates optical flow into its horizontal and vertical components Calculated by taking the gradient of the optical flow to get MBHx and MBHy Implemented NIN, working on testing with it Combine different ReLU from maxout and NIN