NDLI: Weakly supervised object detector learning with model drift detection

Content Provider	IEEE Xplore Digital Library
Author	Siva, P. Tao Xiang
Copyright Year	2011
Description	Author affiliation: School of Electronic Engineering and Computer Science, Queen Mary University of London, E1 4NS, UK (Siva, P.; Tao Xiang)
Abstract	A conventional approach to learning object detectors uses fully supervised learning techniques which assumes that a training image set with manual annotation of object bounding boxes are provided. The manual annotation of objects in large image sets is tedious and unreliable. Therefore, a weakly supervised learning approach is desirable, where the training set needs only binary labels regarding whether an image contains the target object class. In the weakly supervised approach a detector is used to iteratively annotate the training set and learn the object model. We present a novel weakly supervised learning framework for learning an object detector. Our framework incorporates a new initial annotation model to start the iterative learning of a detector and a model drift detection method that is able to detect and stop the iterative learning when the detector starts to drift away from the objects of interest. We demonstrate the effectiveness of our approach on the challenging PASCAL 2007 dataset.
Starting Page	343
Ending Page	350
File Size	3503813
Page Count	8
File Format	PDF
ISBN	9781457711015
ISSN	15505499
e-ISBN	9781457711022
DOI	10.1109/ICCV.2011.6126261
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-11-06
Publisher Place	Spain
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Detectors Training Measurement Histograms Adaptation models Object detection Support vector machines
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Weakly supervised object detection with convex clustering

Multi-fold MIL Training for Weakly Supervised Object Localization

Efficient Detector Adaptation for Object Detection in a Video

Tabula rasa: Model transfer for object category detection

Semi-supervised boosting using visual similarity learning

An HOG-LBP human detector with partial occlusion handling

ConceptLearner: Discovering visual concepts from weakly labeled image collections

Object Classification with Adaptable Regions

Semi-supervised Domain Adaptation with Instance Constraints

Weakly supervised object detector learning with model drift detection

Similar Documents

Weakly supervised object detection with convex clustering

Multi-fold MIL Training for Weakly Supervised Object Localization

Efficient Detector Adaptation for Object Detection in a Video

Tabula rasa: Model transfer for object category detection

Semi-supervised boosting using visual similarity learning

An HOG-LBP human detector with partial occlusion handling

ConceptLearner: Discovering visual concepts from weakly labeled image collections

Object Classification with Adaptable Regions

Semi-supervised Domain Adaptation with Instance Constraints

Weakly supervised object detector learning with model drift detection