Reappraising Domain Generalization in Neural Networks

• URL: http://arxiv.org/abs/2110.07981v1
• Date: Fri, 15 Oct 2021 10:06:40 GMT
• Title: Reappraising Domain Generalization in Neural Networks
• Authors: Sarath Sivaprasad, Akshay Goindani, Vaibhav Garg, Vineet Gandhi
• Abstract summary: Domain generalization (DG) of machine learning algorithms is defined as their ability to learn a domain agnostic hypothesis from multiple training distributions. We find that a straightforward Empirical Risk Minimization (ERM) baseline consistently outperforms existing DG methods. We propose a classwise-DG formulation, where for each class, we randomly select one of the domains and keep it aside for testing.
• Score: 8.06370138649329
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain generalization (DG) of machine learning algorithms is defined as their ability to learn a domain agnostic hypothesis from multiple training distributions, which generalizes onto data from an unseen domain. DG is vital in scenarios where the target domain with distinct characteristics has sparse data for training. Aligning with recent work~\cite{gulrajani2020search}, we find that a straightforward Empirical Risk Minimization (ERM) baseline consistently outperforms existing DG methods. We present ablation studies indicating that the choice of backbone, data augmentation, and optimization algorithms overshadows the many tricks and trades explored in the prior art. Our work leads to a new state of the art on the four popular DG datasets, surpassing previous methods by large margins. Furthermore, as a key contribution, we propose a classwise-DG formulation, where for each class, we randomly select one of the domains and keep it aside for testing. We argue that this benchmarking is closer to human learning and relevant in real-world scenarios. We comprehensively benchmark classwise-DG on the DomainBed and propose a method combining ERM and reverse gradients to achieve the state-of-the-art results. To our surprise, despite being exposed to all domains during training, the classwise DG is more challenging than traditional DG evaluation and motivates more fundamental rethinking on the problem of DG.

Related papers

• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• MADG: Margin-based Adversarial Learning for Domain Generalization [25.45950080930517]
  We propose a novel adversarial learning DG algorithm, MADG, motivated by a margin loss-based discrepancy metric. The proposed MADG model learns domain-invariant features across all source domains and uses adversarial training to generalize well to the unseen target domain. We extensively experiment with the MADG model on popular real-world DG datasets.
  arXiv  Detail & Related papers  (2023-11-14T19:53:09Z)
• 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)
• Towards Reliable Domain Generalization: A New Dataset and Evaluations [45.68339440942477]
  We propose a new domain generalization task for handwritten Chinese character recognition (HCCR) We evaluate eighteen DG methods on the proposed PaHCC dataset and show that the performance of existing methods is still unsatisfactory. Our dataset and evaluations bring new perspectives to the community for more substantial progress.
  arXiv  Detail & Related papers  (2023-09-12T11:29:12Z)
• Federated Domain Generalization: A Survey [12.84261944926547]
  In machine learning, data is often distributed across different devices, organizations, or edge nodes. In response to this challenge, there has been a surge of interest in federated domain generalization. This paper presents the first survey of recent advances in this area.
  arXiv  Detail & Related papers  (2023-06-02T07:55:42Z)
• On Certifying and Improving Generalization to Unseen Domains [87.00662852876177]
  Domain Generalization aims to learn models whose performance remains high on unseen domains encountered at test-time. It is challenging to evaluate DG algorithms comprehensively using a few benchmark datasets. We propose a universal certification framework that can efficiently certify the worst-case performance of any DG method.
  arXiv  Detail & Related papers  (2022-06-24T16:29:43Z)
• 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)
• COLUMBUS: Automated Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption [12.555885317622131]
  We address the challenging domain generalization problem, where a model trained on a set of source domains is expected to generalize well in unseen domains without exposure to their data. We propose Columbus, a method that enforces new feature discovery via a targeted corruption of the most relevant input and multi-level representations of the data.
  arXiv  Detail & Related papers  (2021-09-09T14:52:05Z)
• Domain Generalization: A Survey [146.68420112164577]
  Domain generalization (DG) aims to achieve OOD generalization by only using source domain data for model learning. For the first time, a comprehensive literature review is provided to summarize the ten-year development in DG.
  arXiv  Detail & Related papers  (2021-03-03T16:12:22Z)
• Model-Based Domain Generalization [96.84818110323518]
  We propose a novel approach for the domain generalization problem called Model-Based Domain Generalization. Our algorithms beat the current state-of-the-art methods on the very-recently-proposed WILDS benchmark by up to 20 percentage points.
  arXiv  Detail & Related papers  (2021-02-23T00:59:02Z)
• Sequential Learning for Domain Generalization [81.70387860425855]
  We propose a sequential learning framework for Domain Generalization (DG) We focus on its application to the recently proposed Meta-Learning Domain generalization (MLDG)
  arXiv  Detail & Related papers  (2020-04-03T05:10:33Z)

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.