1. Concept
Compared with domain adaptation , the most significant difference of domain generalization is that the test set cannot be accessed during training .
The loss function of domain generalization can generally be described as the following form:
This formula is divided into three items: the first item represents the linear combination of the weights of each training set , where π is the coefficient that minimizes this item; the second item represents the inter-domain distance , which represents the minimum distance between the target domain and the source domain, Indicates the maximum distance between pairwise combinations of source domains; the third item indicates ideal joint risk, which can be ignored under normal circumstances .
2. Classification
1. Data manipulation
This method is embodied in the operation of the data set, which is mainly divided into data augmentation (Data augmentation) and data generation (Data generation)
Among them, the main way of data enhancement is to adjust the size, color, brightness and contrast of the image, rotate it, add noise and other operations. It can be divided into: relevant data enhancement and confrontational data enhancement according to the direction of its enhancement .
There are three main ways of data generation : VAE, GAN (against generation), Mixup (mixed enhancement), the main purpose is to enhance the generalization ability of the model.
2. Representation learning
The method can be characterized as:
There are four main methods to characterize the characteristics of the domain by learning each part of the above formula
①Kernel-based method : traditional method, mainly relying on nuclear projection techniques
②Domain adversarial learning : confrontation method, based on confrontation network for confusion
③Explicit feature alignment : Explicitly reduce the difference between domains, domain alignment
④Invariant risk minimization : paradigm method
⑤Feature disentanglement : Decoupling, extracting common features in the same category
Mainly divided into two types: 1. UndoBias : Divide the weight into two types (including the common features of all domains and the private features of each domain)
2. Generative modeling : Decoupling using a generative network
3. Learning strategy
①Meta-learning (source learning)
Decompose the source domain into several small tasks
②Ensemble learning (integrated learning)
It is considered that the target domain is a linear combination of source domains, and in actual operation, various results are combined according to certain weights (similar to voting)