Semi-Supervised Self-Training of Object Detection Models

Authors:
Chuck Rosenberg;Martial Hebert;Henry Schneiderman
Affiliations:
Google, Inc., Mountain View, CA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 51

Automatic video annotation by semi-supervised learning with kernel density estimation

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Structure-sensitive manifold ranking for video concept detection

Proceedings of the 15th international conference on Multimedia
Semi-supervised learning of the hidden vector state model for extracting protein-protein interactions

Artificial Intelligence in Medicine
Mutually beneficial learning with application to on-line news classification

Proceedings of the ACM first Ph.D. workshop in CIKM
A semisupervised support vector machines algorithm for BCI systems

Computational Intelligence and Neuroscience - EEG/MEG Signal Processing
Semi-supervised learning of object categories from paired local features

CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Training the Hidden Vector State Model from Un-annotated Corpus

ICCS '07 Proceedings of the 7th international conference on Computational Science, Part II
Watch, Listen & Learn: Co-training on Captioned Images and Videos

ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Semi-supervised kernel density estimation for video annotation

Computer Vision and Image Understanding
Graph-based semi-supervised learning with multiple labels

Journal of Visual Communication and Image Representation
A self-training approach to cost sensitive uncertainty sampling

Machine Learning
The Impact of Reliability Evaluation on a Semi-supervised Learning Approach

ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
Video semantic analysis based on structure-sensitive anisotropic manifold ranking

Signal Processing
Semi-supervised Robust Alternating AdaBoost

CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning

International Journal of Computer Vision
Scaling up semi-supervised learning: an efficient and effective LLGC variant

PAKDD'07 Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data mining
Large-scale bot detection for search engines

Proceedings of the 19th international conference on World wide web
A semi-supervised learning method for motility disease diagnostic

CIARP'07 Proceedings of the Congress on pattern recognition 12th Iberoamerican conference on Progress in pattern recognition, image analysis and applications
Semi-supervised classification and noise detection

FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1
Ant based semi-supervised classification

ANTS'10 Proceedings of the 7th international conference on Swarm intelligence
Weakly supervised classification of objects in images using soft random forests

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
A self-trained ensemble with semisupervised SVM: An application to pixel classification of remote sensing imagery

Pattern Recognition
LIFT: A new framework of learning from testing data for face recognition

Neurocomputing
Online multiple instance boosting for object detection

Neurocomputing
Discriminative semi-supervised learning of dynamical systems for motion estimation

Pattern Recognition
Discriminative deep belief networks for visual data classification

Pattern Recognition
Semi supervised learning for prediction of prosodic phrase boundaries in chinese TTS using conditional random fields

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Fuzzy semi-supervised support vector machines

MLDM'11 Proceedings of the 7th international conference on Machine learning and data mining in pattern recognition
Time-aware co-training for indoors localization in visual lifelogs

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Using weighted nearest neighbor to benefit from unlabeled data

PAKDD'06 Proceedings of the 10th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
Learning Instance Weighted Naive Bayes from labeled and unlabeled data

Journal of Intelligent Information Systems
On-line inverse multiple instance boosting for classifier grids

Pattern Recognition Letters
Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning

Foundations and Trends® in Computer Graphics and Vision
Classification of emotional states in a woz scenario exploiting labeled and unlabeled bio-physiological data

PSL'11 Proceedings of the First IAPR TC3 conference on Partially Supervised Learning
Estimate unlabeled-data-distribution for semi-supervised PU learning

APWeb'12 Proceedings of the 14th Asia-Pacific international conference on Web Technologies and Applications
Double enhancement learning for explicit internal representations: unifying self-enhancement and information enhancement to incorporate information on input variables

Applied Intelligence
A new relational Tri-training system with adaptive data editing for inductive logic programming

Knowledge-Based Systems
Using clustering analysis to improve semi-supervised classification

Neurocomputing
Semi-supervised multiple instance learning based domain adaptation for object detection

Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing
Semi-supervised multitask learning via self-training and maximum entropy discrimination

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Aggregation pheromone metaphor for semi-supervised classification

Pattern Recognition
DTW-D: time series semi-supervised learning from a single example

Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Building a second opinion: learning cross-company data

Proceedings of the 9th International Conference on Predictive Models in Software Engineering
A self-trained semisupervised SVM approach to the remote sensing land cover classification

Computers & Geosciences
Semi-supervised learning of hidden conditional random fields for time-series classification

Neurocomputing
Using objective ground-truth labels created by multiple annotators for improved video classification: A comparative study

Computer Vision and Image Understanding
Activity recognition with android phone using mixture-of-experts co-trained with labeled and unlabeled data

Neurocomputing
Boosting for multiclass semi-supervised learning

Pattern Recognition Letters
Coupling as Strategy for Reducing Concept-Drift in Never-ending Learning Environments

Fundamenta Informaticae - Cognitive Informatics and Computational Intelligence: Theory and Applications
Robust object tracking using enhanced random ferns

The Visual Computer: International Journal of Computer Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in object appearance. Semi-supervised training is a means for reducing' the effort needed to prepare the training set by training the model with a small number of fully labeled examples and an additional set of unlabeled or weakly labeled examples. In this work we present a semi-supervised approach to training object detection systems based on self-training. we implement our approach as a wrapper around the training process of an existing object detector and present empirical results.The key contributions of this empirical study is to demonstrate that a model trained in this manner can achieve results comparable to a model trained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector.