NDLI: Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies

Content Provider	Springer Nature Link
Author	McAuley, Julian J. Ramisa, Arnau Caeta, Tibério S.
Copyright Year	2012
Abstract	The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. These annotations may be imperfect, in the sense that many images contain multiple objects belonging to the label vocabulary. In other words, we have a multi-label problem but the annotations include only a single label (which is not necessarily the most prominent). Such a setting motivates the use of a robust evaluation measure, which allows for a limited number of labels to be predicted and, so long as one of the predicted labels is correct, the overall prediction should be considered correct. This is indeed the type of evaluation measure used to assess algorithm performance in a recent competition on ImageNet data. Optimizing such types of performance measures presents several hurdles even with existing structured output learning methods. Indeed, many of the current state-of-the-art methods optimize the prediction of only a single output label, ignoring this ‘structure’ altogether. In this paper, we show how to directly optimize continuous surrogates of such performance measures using structured output learning techniques with latent variables. We use the output of existing binary classifiers as input features in a new learning stage which optimizes the structured loss corresponding to the robust performance measure. We present empirical evidence that this allows us to ‘boost’ the performance of binary classification on a variety of weakly-supervised labeling problems defined on image taxonomies.
Starting Page	343
Ending Page	361
Page Count	19
File Format	PDF
ISSN	09205691
Journal	International Journal of Computer Vision
Volume Number	104
Issue Number	3
e-ISSN	15731405
Language	English
Publisher	Springer US
Publisher Date	2012-09-01
Publisher Place	Boston
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Image labeling Image tagging Image taxonomies Structured learning Computer Imaging, Vision, Pattern Recognition and Graphics Artificial Intelligence (incl. Robotics) Image Processing and Computer Vision Pattern Recognition
Content Type	Text
Resource Type	Article
Subject	Artificial Intelligence 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

On Taxonomies for Multi-class Image Categorization

Weakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition

Weakly Supervised Localization and Learning with Generic Knowledge

A Framework for Robust Subspace Learning

SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

Tractable Algorithms for Robust Model Estimation

Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

Face Recognition from Caption-Based Supervision

Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies

Similar Documents

On Taxonomies for Multi-class Image Categorization

Weakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition

Weakly Supervised Localization and Learning with Generic Knowledge

A Framework for Robust Subspace Learning

SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

Tractable Algorithms for Robust Model Estimation

Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition

Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation

Face Recognition from Caption-Based Supervision

Optimization of Robust Loss Functions for Weakly-Labeled Image Taxonomies