Learning with Labels of Existing and Nonexisting

11/29/2018
by   Xi-Lin Li, et al.
0

We study the classification or detection problems where the label only suggests whether any instance of a class exists or does not exist in a training sample. No further information, e.g., the number of instances of each class, their locations or relative orders in the training data, is exploited. The model can be learned by maximizing the likelihood of the event that in a given training sample, instances of certain classes exist, while no instance of other classes exists. We use image recognition as the example task to develop our method, although it is applicable to data with higher or lower dimensions without much modification. Our method can be used to learn all convolutional neural networks for object detection and localization, e.g., reading street view house numbers in images with varying sizes, without using any further processing.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2013

Scalable Object Detection using Deep Neural Networks

Deep convolutional neural networks have recently achieved state-of-the-a...
research
06/01/2021

Instance Correction for Learning with Open-set Noisy Labels

The problem of open-set noisy labels denotes that part of training data ...
research
08/30/2018

Nested multi-instance classification

There are classification tasks that take as inputs groups of images rath...
research
12/09/2017

Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery

Fine-grained object recognition that aims to identify the type of an obj...
research
11/19/2021

Learning to Detect Instance-level Salient Objects Using Complementary Image Labels

Existing salient instance detection (SID) methods typically learn from p...
research
02/11/2020

Learning with Out-of-Distribution Data for Audio Classification

In supervised machine learning, the assumption that training data is lab...

Please sign up or login with your details

Forgot password? Click here to reset