Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management

• URL: http://arxiv.org/abs/2212.08356v3
• Date: Sat, 15 Apr 2023 04:03:04 GMT
• Title: Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management
• Authors: Junha Song, Kwanyong Park, InKyu Shin, Sanghyun Woo, Chaoning Zhang, and In So Kweon
• Abstract summary: Test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time. Several works for TTA have shown promising adaptation performances in continuously changing environments. This paper first presents a robust TTA framework with compound domain knowledge management. We then devise novel regularization which modulates the adaptation rates using domain-similarity between the source and the current target domain.
• Score: 75.86903206636741
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and improve its performance during test time (i.e., lifelong adaptation). Several works for TTA have shown promising adaptation performances in continuously changing environments. However, our investigation reveals that existing methods are vulnerable to dynamic distributional changes and often lead to overfitting of TTA models. To address this problem, this paper first presents a robust TTA framework with compound domain knowledge management. Our framework helps the TTA model to harvest the knowledge of multiple representative domains (i.e., compound domain) and conduct the TTA based on the compound domain knowledge. In addition, to prevent overfitting of the TTA model, we devise novel regularization which modulates the adaptation rates using domain-similarity between the source and the current target domain. With the synergy of the proposed framework and regularization, we achieve consistent performance improvements in diverse TTA scenarios, especially on dynamic domain shifts. We demonstrate the generality of proposals via extensive experiments including image classification on ImageNet-C and semantic segmentation on GTA5, C-driving, and corrupted Cityscapes datasets.

Related papers

• Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation [8.425690424016986]
  Continual Test-Time Adaptation (TTA) seeks to adapt a source pre-trained model to continually changing, unlabeled target domains. Inspired by the principles of online K-Means, this paper introduces a novel approach to continual TTA through visual prompting.
  arXiv  Detail & Related papers  (2024-06-15T20:47:38Z)
• Active Test-Time Adaptation: Theoretical Analyses and An Algorithm [51.84691955495693]
  Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. We propose the novel problem setting of active test-time adaptation (ATTA) that integrates active learning within the fully TTA setting.
  arXiv  Detail & Related papers  (2024-04-07T22:31:34Z)
• BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [59.1863462632777]
  Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. This paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring 98% fewer trainable parameters.
  arXiv  Detail & Related papers  (2024-02-13T18:37:53Z)
• Towards Full-scene Domain Generalization in Multi-agent Collaborative Bird's Eye View Segmentation for Connected and Autonomous Driving [54.60458503590669]
  We propose a unified domain generalization framework applicable in both training and inference stages of collaborative perception. We employ an Amplitude Augmentation (AmpAug) method to augment low-frequency image variations, broadening the model's ability to learn. In the inference phase, we introduce an intra-system domain alignment mechanism to reduce or potentially eliminate the domain discrepancy.
  arXiv  Detail & Related papers  (2023-11-28T12:52:49Z)
• AR-TTA: A Simple Method for Real-World Continual Test-Time Adaptation [16.85284386728494]
  We propose to validate test-time adaptation methods using datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift. The proposed method, named AR-TTA, outperforms existing approaches on both synthetic and more real-world benchmarks.
  arXiv  Detail & Related papers  (2023-09-18T19:34:23Z)
• Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification [77.0114672086012]
  Test-time adaptation (TTA) is a technique aimed at enhancing the generalization performance of models by leveraging unlabeled samples solely during prediction. We present a benchmark that systematically evaluates 13 prominent TTA methods and their variants on five widely used image classification datasets.
  arXiv  Detail & Related papers  (2023-07-06T16:59:53Z)
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation [48.039156140237615]
  A Continual Test-Time Adaptation task is proposed to adapt the pre-trained model to continually changing target domains. We design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-06-07T11:18:53Z)
• Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction [3.5139431332194198]
  Test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. We identify and highlight several challenges a self-training based method has to deal with. To prevent the model from becoming biased, we leverage a dataset and model-agnostic certainty and diversity weighting.
  arXiv  Detail & Related papers  (2023-06-01T13:16:10Z)

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.