Dual-stream Feature Augmentation for Domain Generalization
- URL: http://arxiv.org/abs/2409.04699v1
- Date: Sat, 7 Sep 2024 03:41:05 GMT
- Title: Dual-stream Feature Augmentation for Domain Generalization
- Authors: Shanshan Wang, ALuSi, Xun Yang, Ke Xu, Huibin Tan, Xingyi Zhang,
- Abstract summary: We propose a Dual-stream Feature Augmentation(DFA) method by constructing some hard features from two perspectives.
Our approach could achieve state-of-the-art performance for domain generalization.
- Score: 16.495752769624872
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Domain generalization (DG) task aims to learn a robust model from source domains that could handle the out-of-distribution (OOD) issue. In order to improve the generalization ability of the model in unseen domains, increasing the diversity of training samples is an effective solution. However, existing augmentation approaches always have some limitations. On the one hand, the augmentation manner in most DG methods is not enough as the model may not see the perturbed features in approximate the worst case due to the randomness, thus the transferability in features could not be fully explored. On the other hand, the causality in discriminative features is not involved in these methods, which harms the generalization ability of model due to the spurious correlations. To address these issues, we propose a Dual-stream Feature Augmentation~(DFA) method by constructing some hard features from two perspectives. Firstly, to improve the transferability, we construct some targeted features with domain related augmentation manner. Through the guidance of uncertainty, some hard cross-domain fictitious features are generated to simulate domain shift. Secondly, to take the causality into consideration, the spurious correlated non-causal information is disentangled by an adversarial mask, then the more discriminative features can be extracted through these hard causal related information. Different from previous fixed synthesizing strategy, the two augmentations are integrated into a unified learnable feature disentangle model. Based on these hard features, contrastive learning is employed to keep the semantic consistency and improve the robustness of the model. Extensive experiments on several datasets demonstrated that our approach could achieve state-of-the-art performance for domain generalization. Our code is available at: https://github.com/alusi123/DFA.
Related papers
- Causality-inspired Latent Feature Augmentation for Single Domain Generalization [13.735443005394773]
Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains.
Under the domain-hungry configuration, how to expand the coverage of source domain and find intrinsic causal features across different distributions is the key to enhancing the models' generalization ability.
We propose a novel causality-inspired latent feature augmentation method for Single-DG by learning the meta-knowledge of feature-level transformation based on causal learning and interventions.
arXiv Detail & Related papers (2024-06-10T02:42:25Z) - HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain
Generalization [69.33162366130887]
Domain Generalization (DG) endeavors to create machine learning models that excel in unseen scenarios by learning invariant features.
We introduce a novel method designed to supplement the model with domain-level and task-specific characteristics.
This approach aims to guide the model in more effectively separating invariant features from specific characteristics, thereby boosting the generalization.
arXiv Detail & Related papers (2024-01-18T04:23:21Z) - Learning Generalizable Models via Disentangling Spurious and Enhancing
Potential Correlations [28.38895118573957]
Domain generalization (DG) aims to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain.
Adopting multiple perspectives, such as the sample and the feature, proves to be effective.
In this paper, we focus on improving the generalization ability of the model by compelling it to acquire domain-invariant representations from both the sample and feature perspectives.
arXiv Detail & Related papers (2024-01-11T09:00:22Z) - A Contrastive Variational Graph Auto-Encoder for Node Clustering [10.52321770126932]
State-of-the-art clustering methods have numerous challenges.
Existing VGAEs do not account for the discrepancy between the inference and generative models.
Our solution has two mechanisms to control the trade-off between Feature Randomness and Feature Drift.
arXiv Detail & Related papers (2023-12-28T05:07:57Z) - SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation [62.889835139583965]
We introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data.
As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data.
Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.
arXiv Detail & Related papers (2023-04-06T17:36:23Z) - CAusal and collaborative proxy-tasKs lEarning for Semi-Supervised Domain
Adaptation [20.589323508870592]
Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples.
We show that the proposed model significantly outperforms SOTA methods in terms of effectiveness and generalisability on SSDA datasets.
arXiv Detail & Related papers (2023-03-30T16:48:28Z) - Style Interleaved Learning for Generalizable Person Re-identification [69.03539634477637]
We propose a novel style interleaved learning (IL) framework for DG ReID training.
Unlike conventional learning strategies, IL incorporates two forward propagations and one backward propagation for each iteration.
We show that our model consistently outperforms state-of-the-art methods on large-scale benchmarks for DG ReID.
arXiv Detail & Related papers (2022-07-07T07:41:32Z) - 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) - Learning Domain Invariant Representations for Generalizable Person
Re-Identification [71.35292121563491]
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community.
We introduce causality into person ReID and propose a novel generalizable framework, named Domain Invariant Representations for generalizable person Re-Identification (DIR-ReID)
arXiv Detail & Related papers (2021-03-29T18:59:48Z) - Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [61.317911756566126]
We propose a Towards Fair Knowledge Transfer framework to handle the fairness challenge in imbalanced cross-domain learning.
Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness.
Our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.
arXiv Detail & Related papers (2020-10-23T06:29:09Z)
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.