Skip to content
/ MCMIL Public

A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample. Demonstration on multiple object detection and localization.

Notifications You must be signed in to change notification settings

lixilinx/MCMIL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

0330c28 · Aug 24, 2020

History

18 Commits
Nov 29, 2018
Nov 29, 2018
Nov 29, 2018
Nov 29, 2018
Nov 29, 2018
Aug 24, 2020
Nov 29, 2018
Jan 22, 2019
Nov 29, 2018
Nov 29, 2018
Jan 21, 2019
Nov 29, 2018

Repository files navigation

Please check function log_prb_labels() for logarithm bag probability calculation. Although we just demonstrate its application to multiple object detection and localization, this function accepts probability tensor P with other orders, as long as the first dimension is number_of_classes + 1.

We have used this optimization code to train our models. You may try your favorite optimization methods.

We demonstrated its applications to image recognition and street view house number transcription using all convolutional networks. For MNIST, we got test classification error rate slightly higher than 0.3%. For SVHN, we got sequence transcription error rate slightly higher than 5% with a model having about 7.5M coefficients (vs. about 4% by this specialized and strongly supervised model having about 51M coefficients). Our learned model might be able to directly read the numbers in many of the original images as shown below. Preprocessed SVHN dataset and some pretrained models are here.

alt text

About

A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample. Demonstration on multiple object detection and localization.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published