English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification

Lapin, M., Hein, M., & Schiele, B. (2016). Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification. Retrieved from http://arxiv.org/abs/1612.03663.

Item is

Files

show Files
hide Files
:
1612.03663.pdf (Preprint), 8MB
Name:
1612.03663.pdf
Description:
File downloaded from arXiv at 2016-12-21 12:55
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-

Locators

show

Creators

show
hide
 Creators:
Lapin, Maksim1, Author           
Hein, Matthias2, Author
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV,Computer Science, Learning, cs.LG,Statistics, Machine Learning, stat.ML
 Abstract: Top-k error is currently a popular performance measure on large scale image classification benchmarks such as ImageNet and Places. Despite its wide acceptance, our understanding of this metric is limited as most of the previous research is focused on its special case, the top-1 error. In this work, we explore two directions that shed more light on the top-k error. First, we provide an in-depth analysis of established and recently proposed single-label multiclass methods along with a detailed account of efficient optimization algorithms for them. Our results indicate that the softmax loss and the smooth multiclass SVM are surprisingly competitive in top-k error uniformly across all k, which can be explained by our analysis of multiclass top-k calibration. Further improvements for a specific k are possible with a number of proposed top-k loss functions. Second, we use the top-k methods to explore the transition from multiclass to multilabel learning. In particular, we find that it is possible to obtain effective multilabel classifiers on Pascal VOC using a single label per image for training, while the gap between multiclass and multilabel methods on MS COCO is more significant. Finally, our contribution of efficient algorithms for training with the considered top-k and multilabel loss functions is of independent interest.

Details

show
hide
Language(s): eng - English
 Dates: 2016-12-122016
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1612.03663
URI: http://arxiv.org/abs/1612.03663
BibTex Citekey: Lapinarxiv16
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show