因果表征学习

因果图 (Causal Diagram)

如果整个 DAG 的结构已知且所有的变量都可观测，那么我们可以根据上面 do 算子的公式算出任意变量之间的因果作用。但是，在绝大多数的实际问题中，我们既不知道整个 DAG 的结构，也不能将所有的变量观测到。

“后门准则”（backdoor criterion）和“前门准则”（frontdoor criterion）

后门准则：Z可以同时影响or产生 X/Y，那么Z就相当于X/Y因果关系的后门（不影响X-> Y之间，影响两者），Z也是X/Y的混杂因子
前门准则：Z影响X-> Y的前门路径（直接影响X->Y）

后门调整

Z在X-> Y的后门路径上，那么一般会利用do算子进行干预，进行【后门调整】，可以看到这里从do(X) -> (X,z)

Visual Commonsense R-CNN

Causal Intervention for Weakly-Supervised Semantic Segmentation

Causal Intervention and Parameter-Free Reasoning for Few-Shot SAR Target Recognition

A Domain Generalization Network Exploiting Causal Representations and Non-Causal Representations for Three-Phase Converter Fault Diagnosis

Causal Prototype-Inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-Resolution Remote Sensing Imagery

Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation

Generalizable Single-Source Cross-Modality Medical Image Segmentation via Invariant Causal Mechanisms

Causality-inspired Unsupervised Domain Adaptation with Target Style Imitation for Medical Image Segmentation

CPI-Parser: Integrating Causal Properties Into Multiple Human Parsing

Revisiting Few-Shot Learning From a Causal Perspective

Causal Meta-Transfer Learning for Cross-Domain Few-Shot Hyperspectral Image Classification