Domain Alignment Meets Fully Test-Time Adaptation

• URL: http://arxiv.org/abs/2207.04185v1
• Date: Sat, 9 Jul 2022 03:17:19 GMT
• Title: Domain Alignment Meets Fully Test-Time Adaptation
• Authors: Kowshik Thopalli, Pavan Turaga and Jayaraman J. Thiagarajan
• Abstract summary: A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. We propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data.
• Score: 24.546705919244936
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. While fully test-time adaptation (FTTA) and unsupervised domain adaptation (UDA) are closely related, the advances in UDA are not readily applicable to TTA, since most UDA methods require access to the source data. Hence, we propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data, through a novel deep subspace alignment strategy. With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation. Through extensive experimental evaluation on multiple 2D and 3D vision benchmarks (ImageNet-C, Office-31, OfficeHome, DomainNet, PointDA-10) and model architectures, we demonstrate significant gains in FTTA performance. Furthermore, we make a number of crucial findings on the utility of the alignment objective even with inherently robust models, pre-trained ViT representations and under low sample availability in the target domain.

Related papers

• Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation [52.36436121884317]
  We show that Source-Free Domain Adaptation (SFDA) generally outperforms Unsupervised Domain Adaptation (UDA) in real-world scenarios. SFDA offers advantages in time efficiency, storage requirements, targeted learning objectives, reduced risk of negative transfer, and increased robustness against overfitting. We propose a novel weight estimation method that effectively integrates available source data into multi-SFDA approaches.
  arXiv  Detail & Related papers  (2024-11-24T13:49:29Z)
• Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation [6.649910168731417]
  Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data. We propose a novel framework for SFDA that generates source data using a text-to-image diffusion model trained on the target domain samples.
  arXiv  Detail & Related papers  (2023-10-02T23:38:17Z)
• Back to the Source: Diffusion-Driven Test-Time Adaptation [77.4229736436935]
  Test-time adaptation harnesses test inputs to improve accuracy of a model trained on source data when tested on shifted target data. We instead update the target data, by projecting all test inputs toward the source domain with a generative diffusion model.
  arXiv  Detail & Related papers  (2022-07-07T17:14:10Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Source-Free Domain Adaptation via Distribution Estimation [106.48277721860036]
  Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation.
  arXiv  Detail & Related papers  (2022-04-24T12:22:19Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• Black-box Probe for Unsupervised Domain Adaptation without Model Transferring [30.55386853475974]
  Unsupervised domain adaptation (UDA) methods can achieve promising performance without transferring data from source domain to target domain. In many data-critical scenarios, methods based on model transferring may suffer from membership inference attacks and expose private data. We propose Black-box Probe Domain Adaptation (BPDA), which adopts query mechanism to probe and refine information from source model using third-party dataset.
  arXiv  Detail & Related papers  (2021-07-21T16:00:51Z)
• Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data [31.43183992755392]
  We propose a novel Convolutional deep Domain Adaptation model for Time Series data (CoDATS) Second, we propose a novel Domain Adaptation with Weak Supervision (DA-WS) method by utilizing weak supervision in the form of target-domain label distributions. Third, we perform comprehensive experiments on diverse real-world datasets to evaluate the effectiveness of our domain adaptation and weak supervision methods.
  arXiv  Detail & Related papers  (2020-05-22T04:16:58Z)
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation [102.67010690592011]
  Unsupervised adaptationUDA (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model. This work tackles a practical setting where only a trained source model is available and how we can effectively utilize such a model without source data to solve UDA problems.
  arXiv  Detail & Related papers  (2020-02-20T03:13:58Z)

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.