Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
- URL: http://arxiv.org/abs/2406.04609v2
- Date: Sat, 29 Jun 2024 03:15:51 GMT
- Title: Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition
- Authors: Junru Zhang, Lang Feng, Zhidan Liu, Yuhan Wu, Yang He, Yabo Dong, Duanqing Xu,
- Abstract summary: Existing domain generalization methods often face challenges in capturing intra- and inter-domain style diversity.
We propose a process conceptualized as domain padding to enrich the domain diversity.
We introduce a style-fused sampling strategy to enhance data generation diversity.
Our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
- Score: 8.850516669999292
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a broad range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
Related papers
- StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain.
State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data.
We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
arXiv Detail & Related papers (2024-06-01T02:41:34Z) - Cross-Domain Feature Augmentation for Domain Generalization [16.174824932970004]
We propose a cross-domain feature augmentation method named XDomainMix.
Experiments on widely used benchmark datasets demonstrate that our proposed method is able to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-05-14T13:24:19Z) - 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) - Towards Domain-Specific Features Disentanglement for Domain
Generalization [23.13095840134744]
We propose a novel contrastive-based disentanglement method CDDG to exploit the over-looked domain-specific features.
Specifically, CDDG learns to decouple inherent mutually exclusive features by leveraging them in the latent space.
Experiments conducted on various benchmark datasets demonstrate the superiority of our method compared to other state-of-the-art approaches.
arXiv Detail & Related papers (2023-10-04T17:51:02Z) - Improving Anomaly Segmentation with Multi-Granularity Cross-Domain
Alignment [17.086123737443714]
Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems.
While existing methods demonstrate noteworthy results on synthetic data, they often fail to consider the disparity between synthetic and real-world data domains.
We introduce the Multi-Granularity Cross-Domain Alignment framework, tailored to harmonize features across domains at both the scene and individual sample levels.
arXiv Detail & Related papers (2023-08-16T22:54:49Z) - A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain.
The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance.
We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
arXiv Detail & Related papers (2023-08-02T03:16:12Z) - NormAUG: Normalization-guided Augmentation for Domain Generalization [60.159546669021346]
We propose a simple yet effective method called NormAUG (Normalization-guided Augmentation) for deep learning.
Our method introduces diverse information at the feature level and improves the generalization of the main path.
In the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance.
arXiv Detail & Related papers (2023-07-25T13:35:45Z) - Domain Generalization with Correlated Style Uncertainty [4.844240089234632]
Style augmentation is a strong DG method taking advantage of instance-specific feature statistics.
We introduce Correlated Style Uncertainty (CSU), surpassing the limitations of linear generalization in style statistic space.
Our method's efficacy is established through extensive experimentation on diverse cross-domain computer vision and medical imaging classification tasks.
arXiv Detail & Related papers (2022-12-20T01:59:27Z) - Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions.
We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space.
Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
arXiv Detail & Related papers (2022-03-24T11:54:59Z) - Consistency and Diversity induced Human Motion Segmentation [231.36289425663702]
We propose a novel Consistency and Diversity induced human Motion (CDMS) algorithm.
Our model factorizes the source and target data into distinct multi-layer feature spaces.
A multi-mutual learning strategy is carried out to reduce the domain gap between the source and target data.
arXiv Detail & Related papers (2022-02-10T06:23:56Z) - Feature-based Style Randomization for Domain Generalization [27.15070576861912]
Domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaptions.
This paper develops a simple yet effective feature-based style randomization module to achieve feature-level augmentation.
Compared with existing image-level augmentation, our feature-level augmentation favors a more goal-oriented and sample-diverse way.
arXiv Detail & Related papers (2021-06-06T16:34:44Z)
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.