A Causal Inspired Early-Branching Structure for Domain Generalization
- URL: http://arxiv.org/abs/2403.08649v1
- Date: Wed, 13 Mar 2024 16:04:29 GMT
- Title: A Causal Inspired Early-Branching Structure for Domain Generalization
- Authors: Liang Chen, Yong Zhang, Yibing Song, Zhen Zhang, Lingqiao Liu
- Abstract summary: Learning domain-invariant semantic representations is crucial for achieving domain generalization.
Standard training often results in entangled semantic and domain-specific features.
Previous works suggest formulating the problem from a causal perspective.
We propose two strategies as complements for the basic framework.
- Score: 46.55514281988053
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Learning domain-invariant semantic representations is crucial for achieving
domain generalization (DG), where a model is required to perform well on unseen
target domains. One critical challenge is that standard training often results
in entangled semantic and domain-specific features. Previous works suggest
formulating the problem from a causal perspective and solving the entanglement
problem by enforcing marginal independence between the causal (\ie semantic)
and non-causal (\ie domain-specific) features. Despite its simplicity, the
basic marginal independent-based idea alone may be insufficient to identify the
causal feature. By d-separation, we observe that the causal feature can be
further characterized by being independent of the domain conditioned on the
object, and we propose the following two strategies as complements for the
basic framework.
First, the observation implicitly implies that for the same object, the
causal feature should not be associated with the non-causal feature, revealing
that the common practice of obtaining the two features with a shared base
feature extractor and two lightweight prediction heads might be inappropriate.
To meet the constraint, we propose a simple early-branching structure, where
the causal and non-causal feature obtaining branches share the first few blocks
while diverging thereafter, for better structure design; Second, the
observation implies that the causal feature remains invariant across different
domains for the same object. To this end, we suggest that augmentation should
be incorporated into the framework to better characterize the causal feature,
and we further suggest an effective random domain sampling scheme to fulfill
the task. Theoretical and experimental results show that the two strategies are
beneficial for the basic marginal independent-based framework. Code is
available at \url{https://github.com/liangchen527/CausEB}.
Related papers
- Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation [9.453879758234379]
We propose a new framework, named textitDomain Game, to perform better feature distangling for medical image segmentation.
In domain game, a set of randomly transformed images derived from a singular source image is strategically encoded into two separate feature sets.
Results from cross-site test domain evaluation showcase approximately an 11.8% performance boost in prostate segmentation and around 10.5% in brain tumor segmentation.
arXiv Detail & Related papers (2024-06-04T09:10:02Z) - Bridging Domains with Approximately Shared Features [26.096779584142986]
Multi-source domain adaptation aims to reduce performance degradation when applying machine learning models to unseen domains.
Some advocate for learning invariant features from source domains, while others favor more diverse features.
We propose a statistical framework that distinguishes the utilities of features based on the variance of their correlation to label $y$ across domains.
arXiv Detail & Related papers (2024-03-11T04:25:41Z) - Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain
Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery [8.3316355693186]
We propose a prototype-inspired contrast adaptation (CPCA) method to explore the invariant causal mechanisms between different HRSIs domains and their semantic labels.
It disentangles causal features and bias features from the source and target domain images through a causal feature disentanglement module.
To further de-correlate causal and bias features, a causal intervention module is introduced to intervene on the bias features to generate counterfactual unbiased samples.
arXiv Detail & Related papers (2024-03-06T13:39:18Z) - DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
Causality has been combined with machine learning to produce robust representations for domain generalization.
We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy.
We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
arXiv Detail & Related papers (2024-02-29T07:09:01Z) - CILF:Causality Inspired Learning Framework for Out-of-Distribution
Vehicle Trajectory Prediction [0.0]
Trajectory prediction is critical for autonomous driving vehicles.
Most existing methods tend to model the correlation between history trajectory (input) and future trajectory (output)
arXiv Detail & Related papers (2023-07-11T05:21:28Z) - Causality Inspired Representation Learning for Domain Generalization [47.574964496891404]
We introduce a general structural causal model to formalize the Domain generalization problem.
Our goal is to extract the causal factors from inputs and then reconstruct the invariant causal mechanisms.
We highlight that ideal causal factors should meet three basic properties: separated from the non-causal ones, jointly independent, and causally sufficient for the classification.
arXiv Detail & Related papers (2022-03-27T08:08:33Z) - Instrumental Variable-Driven Domain Generalization with Unobserved
Confounders [53.735614014067394]
Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains.
We propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning.
In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain.
In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution.
arXiv Detail & Related papers (2021-10-04T13:32:57Z) - Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information.
Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure.
We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
arXiv Detail & Related papers (2020-02-12T09:45:39Z) - Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
Current adversarial adaptation methods attempt to align the cross-domain features.
Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain.
We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
arXiv Detail & Related papers (2020-02-06T22:58:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.