Object Detection with Bootstrapping Carlos Rubiano Mentor: Oliver Nina

Slides:



Advertisements
Similar presentations
Wei Fan Ed Greengrass Joe McCloskey Philip S. Yu Kevin Drummey
Advertisements

Type Independent Correction of Sample Selection Bias via Structural Discovery and Re-balancing Jiangtao Ren Xiaoxiao Shi Wei Fan Philip S. Yu.
Classification Classification Examples
Random Forest Predrag Radenković 3237/10
Imbalanced data David Kauchak CS 451 – Fall 2013.
My name is Dustin Boswell and I will be presenting: Ensemble Methods in Machine Learning by Thomas G. Dietterich Oregon State University, Corvallis, Oregon.
Autocorrelation and Linkage Cause Bias in Evaluation of Relational Learners David Jensen and Jennifer Neville.
Ensemble Learning: An Introduction
Accuracy of Prediction How accurate are predictions based on a correlation?
Active Learning Strategies for Drug Screening 1. Introduction At the intersection of drug discovery and experimental design, active learning algorithms.
EVALUATION David Kauchak CS 451 – Fall Admin Assignment 3 - change constructor to take zero parameters - instead, in the train method, call getFeatureIndices()
Zhangxi Lin ISQS Texas Tech University Note: Most slides are from Decision Tree Modeling by SAS Lecture Notes 6 Ensembles of Trees.
Associative Pattern Memory (APM) Larry Werth July 14, 2007
Learning Structure in Bayes Nets (Typically also learn CPTs here) Given the set of random variables (features), the space of all possible networks.
ENSEMBLE LEARNING David Kauchak CS451 – Fall 2013.
Jonathan Reagan Umass Dartmouth CSUMS Summer 11 August 3 rd 2011.
Rotation Invariant Neural-Network Based Face Detection
Combining multiple learners Usman Roshan. Bagging Randomly sample training data Determine classifier C i on sampled data Goto step 1 and repeat m times.
Ensemble Learning Spring 2009 Ben-Gurion University of the Negev.
CLASSIFICATION: Ensemble Methods
Manu Chandran. Outline Background and motivation Over view of techniques Cross validation Bootstrap method Setting up the problem Comparing AIC,BIC,Crossvalidation,Bootstrap.
ISQS 6347, Data & Text Mining1 Ensemble Methods. ISQS 6347, Data & Text Mining 2 Ensemble Methods Construct a set of classifiers from the training data.
Prediction of NMR Chemical Shifts. A Chemometrical Approach К.А. Blinov, Y.D. Smurnyy, Т.S. Churanova, М.Е. Elyashberg Advanced Chemistry Development (ACD)
Bayesian Averaging of Classifiers and the Overfitting Problem Rayid Ghani ML Lunch – 11/13/00.
1 Improve Protein Disorder Prediction Using Homology Instructor: Dr. Slobodan Vucetic Student: Kang Peng.
Active learning Haidong Shi, Nanyi Zeng Nov,12,2008.
COP5992 – DATA MINING TERM PROJECT RANDOM SUBSPACE METHOD + CO-TRAINING by SELIM KALAYCI.
Assignments CS fall Assignment 1 due Generate the in silico data set of 2sin(1.5x)+ N (0,1) with 100 random values of x between.
Classification Ensemble Methods 1
COMP24111: Machine Learning Ensemble Models Gavin Brown
Ensemble Methods Construct a set of classifiers from the training data Predict class label of previously unseen records by aggregating predictions made.
A study involving stress is done on a college campus among the students. The stress scores are known to follow a uniform distribution with the lowest stress.
1 Strategy Effects in Naming: A Modified Deadline View Thomas M. Spalek & Steve Joordens University of Toronto at Scarbrough.
Combining multiple learners Usman Roshan. Decision tree From Alpaydin, 2010.
Week 4: 6/6 – 6/10 Jeffrey Loppert. This week.. Coded a Histogram of Oriented Gradients (HOG) Feature Extractor Extracted features from positive and negative.
Assignment 4: Deep Convolutional Neural Networks
9/24/2017 7:27 AM © Microsoft Corporation. All rights reserved. MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN.
Ensemble Classifiers.
Machine Learning: Ensemble Methods
When deep learning meets object detection: Introduction to two technologies: SSD and YOLO Wenchi Ma.
Statistical Inference
Object Classification through Deconvolutional Neural Networks
Sofus A. Macskassy Fetch Technologies
Trees, bagging, boosting, and stacking
Mentor: Afshin Dehghan
Perceptrons Lirong Xia.
CSCI 5922 Neural Networks and Deep Learning Generative Adversarial Networks Mike Mozer Department of Computer Science and Institute of Cognitive Science.
Object Detection with Bootstrapping
Sample space diagrams 1. A blue and a red dice are thrown and the scores added together. (a) Complete the sample space diagram. (b) What is the probability.
REU Report Meetings – Week 7
Generalization ..
Bird-species Recognition Using Convolutional Neural Network
CS 188: Artificial Intelligence
Introduction to Data Mining, 2nd Edition
Face Components detection
Object Classification through Deconvolutional Neural Networks
Multi-Biometrics: Fusing At The Classification Output Level Using Keystroke and Mouse Motion Features Todd Breuer, Paola Garcia Cardenas, Anu George, Hung.
Multiple Decision Trees ISQS7342
Classification of highly unbalanced data using deep learning techniques
Machine Learning Interpretability
YOLO-LITE: A Real-Time Object Detection Web Implementation
Object Classification through Deconvolutional Neural Networks
Ensemble learning.
Somi Jacob and Christian Bach
For First Place Most Times Up at the Table
I can determine the different sampling techniques used in real life.
Perceptrons Lirong Xia.
Report 7 Brandon Silva.
… 1 2 n A B V W C X 1 2 … n A … V … W … C … A X feature 1 feature 2
Evaluation David Kauchak CS 158 – Fall 2019.
Presentation transcript:

Object Detection with Bootstrapping Carlos Rubiano Mentor: Oliver Nina

Began Testing with Multiple Networks Trained 3 Networks with 33%, 50%, 100% randomized dataset Using the trained models from Cifar10 - Tested on same test batch with different networks to obtain predictions Applied different techniques for voting - Voting with labels - Highest probability from 3 networks

Results Possible randomization issue: networks ran with re- sampling score lower Voting did increase accuracy

Used original data for highest scores Tried another voting technique - Adding, averaging, and picking highest Tested with more than 3 networks

Modified code to improve runtime speed - Allows getting probabilities for multiple networks much faster by implementing it into a function and then multi-threading with a bash script