Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Image Classification with Limited Training Data and Class Ambiguity
Speaker:Maksim Lapin
coming from:Max-Planck-Institut für Informatik - D2
Speakers Bio:
Event Type:Promotionskolloquium
Visibility:D1, D2, D3, D4, D5, RG1, SWS, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Monday, 22 May 2017
Time:14:00
Duration:60 Minutes
Location:Saarbrücken
Building:E1 4
Room:024
Abstract
Modern image classification methods are based on supervised learning algorithms that require labeled training data. However, only a limited amount of annotated data may be available in certain applications due to scarcity of the data itself or high costs associated with human annotation. Introduction of additional information and structural constraints can help improve the performance of a learning algorithm. In this talk, we study the framework of learning using privileged information and demonstrate its relation to learning with instance weights. We also consider multitask feature learning and develop an efficient dual optimization scheme that is particularly well suited to problems with high dimensional image descriptors.

Scaling annotation to a large number of image categories leads to the problem of class ambiguity where clear distinction between the classes is no longer possible. Many real world images are naturally multilabel yet the existing annotation might only contain a single label. In this talk, we propose and analyze a number of loss functions that allow for a certain tolerance in top k predictions of a learner. Our results indicate consistent improvements over the standard loss functions that put more penalty on the first incorrect prediction compared to the proposed losses.

Contact
Name(s):Connie Balzert
Phone:9325-2000
EMail:cbalzert@mpi-inf.mpg.de
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created:
Connie Balzert/MPI-INF, 05/09/2017 11:12 AM
Last modified:
halma/MPII/DE, 03/22/2018 12:00 AM
  • Connie Balzert, 05/09/2017 11:12 AM -- Created document.