Overview of Zero-Shot learning - 1.2

Learning Settings 1.2

• The goal of Zero-Shot Learning： learn the Classifier $f^u(\cdot)$.

• During Model learning : if Information about testing instances is involved , the learned model is transductive for these specific testing instances.

• In Zero-Shot Learning , this transduction can be embodied in two progressive degrees:

  • Transductive for specific unseen classes
  • Transductive for specific testing instances

    This is different from the well-known transductive setting in semisupervised learning . which is just for the testing instances .

  In the seeting that is transductive for specific testing instances , The transductive degree goes further.
  The testing instances are also involved in model learning . and the model is optimized for these specific testing instances.
  Based on the degree of transduction, we categorize zero-shot learning into three learning settings:

  • Class-Inductive Instance-Inductive Setting(CIII) ：

    Only labeled training instances $D^{tr}$ and seen class prototypes $T^{s}$ are used in model learning.

  • Class-transductive Instance-Inductive Setting(“CTII”)

    Labeled traning instances $D^{tr}$， seen class protptypes $T^s$, unseen class prototype $T^u$ are used in model learning .

  • Class-Transductive Instance-Transductive Setting(“CTIT”)

    Labeled training instances $D^{tr}$, seen class protptypes $T^s$，unlabeled testing instances $X^{te}$， and unseen class prototypes $T^s$，unlabeled testing instances $X^te$ ， and unseen class prototypes $T^u$ are used in model learning .

  
  As Fig.1 we can see, from CIII to CTIT ， the classifier $f^{u}(\dot)$ is learned with increasingly specific testing instances 's information .

In machine-learning methods , as the distributions of the training and the testing instances are different , the performance of the model learned with the training instances will decrease when applied to the testing instances.
This phenomenon is more severe in zero-shot learning , as the classes covered by the training and the testing instances are disjoint , this phenomenon is usually referred to as domain shift.

 Under the CIII setting , as no information about the testing instances is involved in model learning , the problem of domain shift is severe in some methods under this setting. 
 However , as the models under this setting are not optimized for specific unseen classes testing instances , when new unseen classes or testing instances need to be classified , the generalization ability of models learned under this setting is usually better than models learned under the CTTI of CTIT settings. 


 Under the CTII setting , as the unseen class prototypes are involved in model learning , the problem of domain shift is less severe . 
 However , the ability of CTII methods to generalize to new unseen classes is limited. 


 Under the CTIT setting , as the models are otimied for specific unseen classes and testing instances , the problem of domain shift is the least sefere among these three learning settings. 
 However , the generalization ability to new unseen classes and testing instances is also the most limited. 

We will introduce methods In Section 3, under these three learning settings separately .

扫描二维码关注公众号，回复： 6237681 查看本文章