BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

• URL: http://arxiv.org/abs/2402.08712v3
• Date: Fri, 31 May 2024 21:14:42 GMT
• Title: BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
• Authors: Daeun Lee, Jaehong Yoon, Sung Ju Hwang,
• Abstract summary: 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.
• Score: 59.1863462632777
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations.

Related papers

• Adaptive Conditional Expert Selection Network for Multi-domain Recommendation [10.418133538132635]
  Mixture-of-Experts (MOE) has recently become the de facto standard in Multi-domain recommendation (MDR) CESAA consists of Conditional Expert Selection (CES) Module and Adaptive Expert Aggregation (AEA) Module. AEA utilizes mutual information loss to strengthen the correlations between experts and specific domains, and significantly improve the distinction between experts.
  arXiv  Detail & Related papers  (2024-11-11T09:39:31Z)
• Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection [14.382503104075917]
  Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios. We propose Hybrid-TTA, a holistic approach that dynamically selects instance-wise tuning method for optimal adaptation. Our approach achieves a notable 1.6%p improvement in mIoU on the Cityscapes-to-ACDC benchmark dataset.
  arXiv  Detail & Related papers  (2024-09-13T06:36:31Z)
• Distribution-Aware Continual Test-Time Adaptation for Semantic Segmentation [33.75630514826721]
  We propose a distribution-aware tuning ( DAT) method to make semantic segmentation CTTA efficient and practical in real-world applications. DAT adaptively selects and updates two small groups of trainable parameters based on data distribution during the continual adaptation process. We conduct experiments on two widely-used semantic segmentation CTTA benchmarks, achieving promising performance compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-24T10:48:20Z)
• Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management [75.86903206636741]
  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.
  arXiv  Detail & Related papers  (2022-12-16T09:02:01Z)
• Towards Unsupervised Domain Adaptation via Domain-Transformer [0.0]
  We propose the Domain-Transformer (DoT) for Unsupervised Domain Adaptation (UDA) DoT integrates the CNN-backbones and the core attention mechanism of Transformers from a new perspective. It achieves the local semantic consistency across domains, where the domain-level attention and manifold regularization are explored.
  arXiv  Detail & Related papers  (2022-02-24T02:30:15Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification [115.31432027711202]
  We argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. We name two-stream adaptive learning (TAL) to simultaneously model these two kinds of information. Our framework can be applied to both single-source and multi-source domain generalization tasks.
  arXiv  Detail & Related papers  (2021-11-29T01:27:42Z)
• A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework [27.13101555533594]
  unsupervised domain adaptation (UDA) techniques are proposed to bridge the gap between different domains. In this paper, we propose a bidirectional UDA framework based on disentangled representation learning for equally competent two-way UDA performances.
  arXiv  Detail & Related papers  (2021-08-18T05:25:11Z)
• Cross-domain Imitation from Observations [50.669343548588294]
  Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. In this paper, we study the problem of how to imitate tasks when there exist discrepancies between the expert and agent MDP. We present a novel framework to learn correspondences across such domains.
  arXiv  Detail & Related papers  (2021-05-20T21:08:25Z)
• 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.