From 8ce886e5d2e0310c3f97d53bc3615dbeee239269 Mon Sep 17 00:00:00 2001
From: lixilinx <37510137+lixilinx@users.noreply.github.com>
Date: Mon, 21 Jan 2019 20:14:41 -0800
Subject: [PATCH] Update README.md

---
 README.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index d008f22..bb729f8 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,8 @@
-# Learning with Labels of Existing/Nonexisting
-A multiclass multiple instance learning method. Only need to know whether any instance of a class exists or not in a sample.
+### Multiclass multiple instance learning
 
-We used [this optimization code](https://github.com/lixilinx/psgd_torch/blob/master/preconditioned_stochastic_gradient_descent.py) to train our models. You may try your favorite optimization methods.
+Please check function [log_prb_labels()](https://github.com/lixilinx/MCMIL/blob/04ad08465d45b2ee8d6174eb1f76dc809550eb16/utilities.py#L6) 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](https://github.com/lixilinx/psgd_torch/blob/master/preconditioned_stochastic_gradient_descent.py) 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 model](https://arxiv.org/abs/1312.6082) having about 51M coefficients and trained with detailed annotations). 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](https://drive.google.com/drive/folders/1BvVpUw3OY3RtkJo-bfujwBsa0y6e49lZ).