Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis

• URL: http://arxiv.org/abs/2402.16090v1
• Date: Sun, 25 Feb 2024 13:37:36 GMT
• Title: Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis
• Authors: Andrea Maracani, Raffaello Camoriano, Elisa Maiettini, Davide Talon, Lorenzo Rosasco and Lorenzo Natale
• Abstract summary: This study provides a benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification. The study empirically examines a diverse set of SF-UDA techniques, assessing their consistency across datasets. It exhaustively evaluates pre-training datasets and strategies, particularly focusing on both supervised and self-supervised methods.
• Score: 16.0130560365211
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design factors in SF-UDA methods. The study empirically examines a diverse set of SF-UDA techniques, assessing their consistency across datasets, sensitivity to specific hyperparameters, and applicability across different families of backbone architectures. Moreover, it exhaustively evaluates pre-training datasets and strategies, particularly focusing on both supervised and self-supervised methods, as well as the impact of fine-tuning on the source domain. Our analysis also highlights gaps in existing benchmark practices, guiding SF-UDA research towards more effective and general approaches. It emphasizes the importance of backbone architecture and pre-training dataset selection on SF-UDA performance, serving as an essential reference and providing key insights. Lastly, we release the source code of our experimental framework. This facilitates the construction, training, and testing of SF-UDA methods, enabling systematic large-scale experimental analysis and supporting further research efforts in this field.

Related papers

• Test-Time Domain Generalization for Face Anti-Spoofing [60.94384914275116]
  Face Anti-Spoofing (FAS) is pivotal in safeguarding facial recognition systems against presentation attacks. We introduce a novel Test-Time Domain Generalization framework for FAS, which leverages the testing data to boost the model's generalizability. Our method, consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS), effectively projects the unseen data to the seen domain space.
  arXiv  Detail & Related papers  (2024-03-28T11:50:23Z)
• A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes [0.8895157045883034]
  This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem. It includes diverse, complementary label feedback, alleviating the effect of incorrect feedback and promoting pseudo-label refinement. We conducted a series of comprehensive experiments, including an ablation analysis, covering a range of partial domain adaptation tasks.
  arXiv  Detail & Related papers  (2023-09-07T07:26:27Z)
• Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics [9.612556145185431]
  Face presentation attack detection (PAD) uses domain adaptation (DA) and domain generalization (DG) techniques to address performance degradation on unknown domains. Most DG-based PAD solutions rely on a priori, i.e., known domain labels. This paper proposes to model face PAD as a compound DG task from a causal perspective, linking it to model optimization.
  arXiv  Detail & Related papers  (2023-08-28T13:11:05Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• NormAUG: Normalization-guided Augmentation for Domain Generalization [60.159546669021346]
  We propose a simple yet effective method called NormAUG (Normalization-guided Augmentation) for deep learning. Our method introduces diverse information at the feature level and improves the generalization of the main path. In the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance.
  arXiv  Detail & Related papers  (2023-07-25T13:35:45Z)
• CAusal and collaborative proxy-tasKs lEarning for Semi-Supervised Domain Adaptation [20.589323508870592]
  Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. We show that the proposed model significantly outperforms SOTA methods in terms of effectiveness and generalisability on SSDA datasets.
  arXiv  Detail & Related papers  (2023-03-30T16:48:28Z)
• A Comprehensive Survey on Source-free Domain Adaptation [69.17622123344327]
  The research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years. We provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme. We compare the results of more than 30 representative SFDA methods on three popular classification benchmarks.
  arXiv  Detail & Related papers  (2023-02-23T06:32:09Z)
• Key Design Choices for Double-Transfer in Source-Free Unsupervised Domain Adaptation [18.21955526087808]
  This paper provides the first in-depth analysis of the main design choices in Source-Free Unsupervised Domain Adaptation (SF-UDA) We pinpoint the normalization approach, pre-training strategy, and backbone architecture as the most critical factors. We show that SF-UDA is competitive also beyond standard benchmarks and backbone architectures, performing on par with UDA at a fraction of the data and computational cost.
  arXiv  Detail & Related papers  (2023-02-10T17:00:37Z)
• A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis [58.124424775536326]
  We propose a simple but effective technique based on mutual information to extract their term. Experiment results show that our proposed method outperforms the state-of-the-art methods for cross-domain ABSA by 4.32% Micro-F1.
  arXiv  Detail & Related papers  (2022-01-29T10:18:07Z)
• A Field Guide to Federated Optimization [161.3779046812383]
  Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data. This paper provides recommendations and guidelines on formulating, designing, evaluating and analyzing federated optimization algorithms.
  arXiv  Detail & Related papers  (2021-07-14T18:09:08Z)

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.