ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2303.14333
8
11

Train/Test-Time Adaptation with Retrieval

25 March 2023
L. Zancato
Alessandro Achille
Tian Yu Liu
Matthew Trager
Pramuditha Perera
Stefano Soatto
    TTA
    OOD
ArXivPDFHTML
Abstract

We introduce Train/Test-Time Adaptation with Retrieval (T3AR{\rm T^3AR}T3AR), a method to adapt models both at train and test time by means of a retrieval module and a searchable pool of external samples. Before inference, T3AR{\rm T^3AR}T3AR adapts a given model to the downstream task using refined pseudo-labels and a self-supervised contrastive objective function whose noise distribution leverages retrieved real samples to improve feature adaptation on the target data manifold. The retrieval of real images is key to T3AR{\rm T^3AR}T3AR since it does not rely solely on synthetic data augmentations to compensate for the lack of adaptation data, as typically done by other adaptation algorithms. Furthermore, thanks to the retrieval module, our method gives the user or service provider the possibility to improve model adaptation on the downstream task by incorporating further relevant data or to fully remove samples that may no longer be available due to changes in user preference after deployment. First, we show that T3AR{\rm T^3AR}T3AR can be used at training time to improve downstream fine-grained classification over standard fine-tuning baselines, and the fewer the adaptation data the higher the relative improvement (up to 13%). Second, we apply T3AR{\rm T^3AR}T3AR for test-time adaptation and show that exploiting a pool of external images at test-time leads to more robust representations over existing methods on DomainNet-126 and VISDA-C, especially when few adaptation data are available (up to 8%).

View on arXiv
Comments on this paper