On Certifying and Improving Generalization to Unseen Domains

• URL: http://arxiv.org/abs/2206.12364v1
• Date: Fri, 24 Jun 2022 16:29:43 GMT
• Title: On Certifying and Improving Generalization to Unseen Domains
• Authors: Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen and Jihun Hamm
• Abstract summary: 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.
• Score: 87.00662852876177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain Generalization (DG) aims to learn models whose performance remains high on unseen domains encountered at test-time by using data from multiple related source domains. Many existing DG algorithms reduce the divergence between source distributions in a representation space to potentially align the unseen domain close to the sources. This is motivated by the analysis that explains generalization to unseen domains using distributional distance (such as the Wasserstein distance) to the sources. However, due to the openness of the DG objective, it is challenging to evaluate DG algorithms comprehensively using a few benchmark datasets. In particular, we demonstrate that the accuracy of the models trained with DG methods varies significantly across unseen domains, generated from popular benchmark datasets. This highlights that the performance of DG methods on a few benchmark datasets may not be representative of their performance on unseen domains in the wild. To overcome this roadblock, we propose a universal certification framework based on distributionally robust optimization (DRO) that can efficiently certify the worst-case performance of any DG method. This enables a data-independent evaluation of a DG method complementary to the empirical evaluations on benchmark datasets. Furthermore, we propose a training algorithm that can be used with any DG method to provably improve their certified performance. Our empirical evaluation demonstrates the effectiveness of our method at significantly improving the worst-case loss (i.e., reducing the risk of failure of these models in the wild) without incurring a significant performance drop on benchmark datasets.

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)
• Non-stationary Domain Generalization: Theory and Algorithm [11.781050299571692]
  In this paper, we study domain generalization in non-stationary environment. We first examine the impact of environmental non-stationarity on model performance. Then, we propose a novel algorithm based on adaptive invariant representation learning.
  arXiv  Detail & Related papers  (2024-05-10T21:32:43Z)
• PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization [24.413415998529754]
  We propose a new benchmark Hybrid Domain Generalization (HDG) and a novel metric $H2$-CV, which construct various splits to assess the robustness of algorithms. Our method outperforms state-of-the-art algorithms on multiple datasets, especially improving the robustness when confronting data scarcity.
  arXiv  Detail & Related papers  (2024-04-13T13:41:13Z)
• 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 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)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Open-Set Domain Adaptation with Visual-Language Foundation Models [51.49854335102149]
  Unsupervised domain adaptation (UDA) has proven to be very effective in transferring knowledge from a source domain to a target domain with unlabeled data. Open-set domain adaptation (ODA) has emerged as a potential solution to identify these classes during the training phase.
  arXiv  Detail & Related papers  (2023-07-30T11:38:46Z)
• Reappraising Domain Generalization in Neural Networks [8.06370138649329]
  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.
  arXiv  Detail & Related papers  (2021-10-15T10:06:40Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• Dual Distribution Alignment Network for Generalizable Person Re-Identification [174.36157174951603]
  Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID) We present a Dual Distribution Alignment Network (DDAN) which handles this challenge by selectively aligning distributions of multiple source domains. We evaluate our DDAN on a large-scale Domain Generalization Re-ID (DG Re-ID) benchmark.
  arXiv  Detail & Related papers  (2020-07-27T00:08:07Z)

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.