DEJA VU: Continual Model Generalization For Unseen Domains

• URL: http://arxiv.org/abs/2301.10418v1
• Date: Wed, 25 Jan 2023 05:56:53 GMT
• Title: DEJA VU: Continual Model Generalization For Unseen Domains
• Authors: Chenxi Liu, Lixu Wang, Lingjuan Lyu, Chen Sun, Xiao Wang, Qi Zhu
• Abstract summary: In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. We propose RaTP, a framework that focuses on improving models' target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA
• Score: 38.700426892171336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptation ability. However, these DA methods typically only provide good performance after a long period of adaptation, and perform poorly on new domains before and during adaptation - in what we call the "Unfamiliar Period", especially when domain shifts happen suddenly and significantly. On the other hand, domain generalization (DG) methods have been proposed to improve the model generalization ability on unadapted domains. However, existing DG works are ineffective for continually changing domains due to severe catastrophic forgetting of learned knowledge. To overcome these limitations of DA and DG in handling the Unfamiliar Period during continual domain shift, we propose RaTP, a framework that focuses on improving models' target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP includes a training-free data augmentation module to prepare data for TDG, a novel pseudo-labeling mechanism to provide reliable supervision for TDA, and a prototype contrastive alignment algorithm to align different domains for achieving TDG, TDA and FA. Extensive experiments on Digits, PACS, and DomainNet demonstrate that RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA and FA capabilities.

Related papers

• Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler [45.71475375161575]
  In Open-Set Domain Generalization, the model is exposed to both new variations of data appearance (domains) and open-set conditions. We propose the Evidential Bi-Level Hardest Domain Scheduler (EBiL-HaDS) to achieve an adaptive domain scheduler.
  arXiv  Detail & Related papers  (2024-09-26T05:57:35Z)
• 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)
• Diverse Target and Contribution Scheduling for Domain Generalization [34.29652655561764]
  Generalization under the distribution shift has been a great challenge in computer vision. We propose a new paradigm for DG called Diverse Target and Contribution Scheduling (DTCS) DTCS comprises two innovative modules: Diverse Target Supervision (DTS) and Diverse Contribution Balance (DCB)
  arXiv  Detail & Related papers  (2023-09-28T14:10:25Z)
• Adaptive Domain Generalization via Online Disagreement Minimization [17.215683606365445]
  Domain Generalization aims to safely transfer a model to unseen target domains. AdaODM adaptively modifies the source model at test time for different target domains. Results show AdaODM stably improves the generalization capacity on unseen domains.
  arXiv  Detail & Related papers  (2022-08-03T11:51:11Z)
• 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)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• Self-supervised Autoregressive Domain Adaptation for Time Series Data [9.75443057146649]
  Unsupervised domain adaptation (UDA) has successfully addressed the domain shift problem for visual applications. These approaches may have limited performance for time series data due to the following reasons. We propose a Self-supervised Autoregressive Domain Adaptation (SLARDA) framework to address these limitations.
  arXiv  Detail & Related papers  (2021-11-29T08:17:23Z)
• 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)
• 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)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

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.