title: SSL Review -2
date: 2019-03-10 10:10:25
tags: SSL
mathjax: true
Overview of Zero-Shot learning
-
the seen classes
- the classes covered by labeled training instances in the feauture space
-
the unseen classes
- unlabeled testing instances in the feature space which belong to another set of classes
-
the feature space
- a real number space
- each instance is represented as a vector within it
- each instance is usually assumed to belong to one class
-
definition
- the Set of Seen Classes:
- a seen classes:
- the Set of Unseen Classes:
- an unseen class:
- Denote that :
- The Feature Space: , which is :
- The set of labeled training instances belonging to seen classes:
- for each labeled instance
,
- :the instance in the feature space ,
- : the corresponding class label .
- The set of testing instances:
where each is a testing instance in the feature space. - The corresponding class labels for
:
which are able to be predicted.
- the Set of Seen Classes:
Definition 1.1 (Zero-Shot Learning)
-
Given labeled training instances belonging to the seen classes ,zero-shot learning aims to learn a classifier that can classify testing instances (i.e. to predict ) belonging to the unseen classes .
-
General idea:
- transfer the knowledge contained in the training instances to the task of testing instance classfication.
- The label spaces covered by the training and the testing instances are disjoint.
- Zero-Shot learning is a subfield of transfer learning. -
Transfer learning
- knowledge contained in the source domain and source task is transferred to the target domain for learning the model in the target task.
- Transfer learning can be classified into :
1、homogeneous transfer learning
>>the feature spaces and the label spaces are the same.
2、heterogeneous transfer learning
>>the feature spaces and/or the label spaces are different.
- Zero-shot learning:
>> the source feature space is the feature space of training instances.
>> the target feature space is the feature space of testing instances.
>> they are the same , both are .
>>the source label space is the seen class set
>> the target label space is the unseen class set
>>Belong to heterogeneous transfer learning with different label spaces(briefly: HTL-DLS) -
Many existing methods for HTL-DLS are proposed for problems under the setting in which there are some labeled instances for the target label space classes .
-
However in Zero-Shot learning,no labeled instances belonging to the target space classes(the unseen classes ) are available .
-
Auxiliary information for the no labeled instances problem in zero-shot learning problem.
- Should contain information about all of the unseen classes.
- This is to guarantee that each of the unseen classes is provided with corresponding auxiliary information.
- Should be related to the instances in the feature space.
- This is to guarantee that the auxiliary information is usable.
-
Existing works.
-
The approach to involve auxiliary information is inspired by the way human beings recognize the world.
-
Humans can perform zero-shot learning with the help of some semantic background knowledge.
-for example: with the knowldge that" a zebra looks like a horse, and with stripes."
we can recognize a zebra even without having seen one before, as long as we know what a horse looks like and what the pattern “stripe” looks like. -
The Auxiliary information involved by existing zero-shot learning methods is usually some Semantic information.
-
It forms a space that contains both the seen and the unseen classes(Refer to Semantic Space)
-
Semantic Space:
- similar to the feature space, is usually a real number space
- each class has a corresponding vector representation , (refered to as the Class prototype or prototype for short of this class)
- We denote
as the Semantic Space :
- is M-dimensional,usually .
- as the class prototypes for seen class .
- as the class prptotype for unseen class
- Denote as the set of protptypes for seen classes
- Denote as the set of prototypes for unseen class
- Denote as a class prototyping function that takes a class label as input, and outputs the corresponding class prototype.
- In zero-shot learning ,
、
、
involved in obtaining the zero-shot classifier
.
-