Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2308.03097v2
• Date: Wed, 18 Jun 2025 12:18:26 GMT
• Title: Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
• Authors: Yinsong Xu, Aidong Men, Yang Liu, Xiahai Zhuang, Qingchao Chen,
• Abstract summary: In deep learning, initializing models with pre-trained weights has become the de facto practice for various downstream tasks.<n>Many unsupervised domain adaptation (UDA) methods typically adopt a backbone pre-trained on ImageNet.<n>We propose a novel framework, named TriDA, to address the impact of pre-training on adaptation.
• Score: 29.989907089369375
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In deep learning, initializing models with pre-trained weights has become the de facto practice for various downstream tasks. Many unsupervised domain adaptation (UDA) methods typically adopt a backbone pre-trained on ImageNet, and focus on reducing the source-target domain discrepancy. However, the impact of pre-training on adaptation received little attention. In this study, we delve into UDA from the novel perspective of pre-training. We first demonstrate the impact of pre-training by analyzing the dynamic distribution discrepancies between pre-training data domain and the source/ target domain during adaptation. Then, we reveal that the target error also stems from the pre-training in the following two factors: 1) empirically, target error arises from the gradually degenerative pre-trained knowledge during adaptation; 2) theoretically, the error bound depends on difference between the gradient of loss function, \ie, on the target domain and pre-training data domain. To address these two issues, we redefine UDA as a three-domain problem, \ie, source domain, target domain, and pre-training data domain; then we propose a novel framework, named TriDA. We maintain the pre-trained knowledge and improve the error bound by incorporating pre-training data into adaptation for both vanilla UDA and source-free UDA scenarios. For efficiency, we introduce a selection strategy for pre-training data, and offer a solution with synthesized images when pre-training data is unavailable during adaptation. Notably, TriDA is effective even with a small amount of pre-training or synthesized images, and seamlessly complements the two scenario UDA methods, demonstrating state-of-the-art performance across multiple benchmarks. We hope our work provides new insights for better understanding and application of domain adaptation.

Related papers

• Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition [1.2878987353423252]
  Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR) We introduce the Stratified Domain Adaptation (StrDA) approach, which examines the gradual escalation of the domain gap for the learning process. We propose a novel method for employing domain discriminators to estimate the out-of-distribution and domain discriminative levels of data samples.
  arXiv  Detail & Related papers  (2024-10-13T16:40:48Z)
• CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection [14.063365469339812]
  LiDAR-based 3D Object Detection methods often do not generalize well to target domains outside the source (or training) data distribution. We introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which leverages visual semantic cues from an image modality. We also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features.
  arXiv  Detail & Related papers  (2024-03-06T14:12:38Z)
• Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision [16.027843524655516]
  We study a practical problem of Source-Free Domain Adaptation (SFDA), which eliminates the reliance on annotated source data. Current SFDA methods focus on extracting domain knowledge from the source-trained model but neglects the intrinsic structure of the target domain. We propose a new SFDA framework, called Region-to-Pixel Adaptation Network(RPANet), which learns the region-level and pixel-level discriminative representations through coarse-to-fine self-supervision.
  arXiv  Detail & Related papers  (2023-08-13T02:37:08Z)
• Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation [108.33885637197614]
  Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or unseen target domains. We propose HRDA, a multi-resolution framework for UDA&DG, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention.
  arXiv  Detail & Related papers  (2023-04-26T15:18:45Z)
• SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation [62.889835139583965]
  We introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real scenarios.
  arXiv  Detail & Related papers  (2023-04-06T17:36:23Z)
• Domain-aware Triplet loss in Domain Generalization [0.0]
  Domain shift is caused by discrepancies in the distributions of the testing and training data. We design a domainaware triplet loss for domain generalization to help the model to cluster similar semantic features. Our algorithm is designed to disperse domain information in the embedding space.
  arXiv  Detail & Related papers  (2023-03-01T14:02:01Z)
• Domain Adaptation with Adversarial Training on Penultimate Activations [82.9977759320565]
  Enhancing model prediction confidence on unlabeled target data is an important objective in Unsupervised Domain Adaptation (UDA) We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features.
  arXiv  Detail & Related papers  (2022-08-26T19:50:46Z)
• Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives [16.68091981866261]
  Unsupervised domain adaptation (UDA) is proposed to counter the performance drop on data in a target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc.
  arXiv  Detail & Related papers  (2022-08-15T20:05:07Z)
• ProCST: Boosting Semantic Segmentation using Progressive Cyclic Style-Transfer [38.03127458140549]
  We propose a novel two-stage framework for improving domain adaptation techniques. In the first step, we progressively train a multi-scale neural network to perform an initial transfer between the source data to the target data. This new data has a reduced domain gap from the desired target domain, and the applied UDA approach further closes the gap.
  arXiv  Detail & Related papers  (2022-04-25T18:01:05Z)
• Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training [57.25828870799331]
  We propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. We develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain. STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset.
  arXiv  Detail & Related papers  (2022-04-25T12:23:07Z)
• 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)
• Continual Test-Time Domain Adaptation [94.51284735268597]
  Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. CoTTA is easy to implement and can be readily incorporated in off-the-shelf pre-trained models.
  arXiv  Detail & Related papers  (2022-03-25T11:42:02Z)
• Domain Adaptation for Real-World Single View 3D Reconstruction [1.611271868398988]
  unsupervised domain adaptation can be used to transfer knowledge from the labeled synthetic source domain to the unlabeled real target domain. We propose a novel architecture which takes advantage of the fact that in this setting, target domain data is unsupervised with regards to the 3D model but supervised for class labels. Results are performed with ShapeNet as the source domain and domains within the Object Domain Suite (ODDS) dataset as the target.
  arXiv  Detail & Related papers  (2021-08-24T22:02:27Z)
• Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [90.71745178767203]
  Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. Existing 3D domain adaptive detection methods often assume prior access to the target domain annotations, which is rarely feasible in the real world. We study a more realistic setting, unsupervised 3D domain adaptive detection, which only utilizes source domain annotations.
  arXiv  Detail & Related papers  (2021-07-23T17:19:23Z)
• UDALM: Unsupervised Domain Adaptation through Language Modeling [79.73916345178415]
  We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss. Our experiments show that performance of models trained with the mixed loss scales with the amount of available target data can be effectively used as a stopping criterion. Our method is evaluated on twelve domain pairs of the Amazon Reviews Sentiment dataset, yielding $91.74%$ accuracy, which is an $1.11%$ absolute improvement over the state-of-versathe-art.
  arXiv  Detail & Related papers  (2021-04-14T19:05:01Z)
• Distill and Fine-tune: Effective Adaptation from a Black-box Source Model [138.12678159620248]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge in previous related labeled datasets (source) to a new unlabeled dataset (target) We propose a novel two-step adaptation framework called Distill and Fine-tune (Dis-tune)
  arXiv  Detail & Related papers  (2021-04-04T05:29:05Z)
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization [43.024669990477214]
  We present a study of domain adaptation for the abstractive summarization task across six diverse target domains in a low-resource setting. Experiments show that the effectiveness of pre-training is correlated with the similarity between the pre-training data and the target domain task.
  arXiv  Detail & Related papers  (2021-03-21T08:12:19Z)
• Don't Stop Pretraining: Adapt Language Models to Domains and Tasks [81.99843216550306]
  We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks. A second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains. Adapting to the task's unlabeled data (task-adaptive pretraining) improves performance even after domain-adaptive pretraining.
  arXiv  Detail & Related papers  (2020-04-23T04:21:19Z)

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.