Jul 2024· International Journal of Machine Learning and Cybernetics· Vol 17· 9 citations· 56 references
Computer Science
TL;DR
Efficient Unsupervised Domain Adaptation (EUDA) is proposed, a parameter-efficient framework that leverages a frozen DINOv2 backbone as a feature extractor and updates only a lightweight bottleneck and classification head to promote both discriminative learning and cross-domain alignment.
Abstract
Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data. Despite recent advances, existing methods often rely on fine-tuning large backbone models, which leads to high computational cost and limits scalability in resource-constrained environments. This limitation highlights the need for parameter-efficient approaches that maintain strong performance with reduced training complexity. Self-supervised foundation models such as DINOv2 provide highly transferable representations and raise the question of whether effective domain adaptation can be achieved without full fine-tuning. To address this question, we propose Efficient Unsupervised Domain Adaptation (EUDA), a parameter-efficient framework that leverages a frozen DINOv2 backbone as a feature extractor and updates only a lightweight bottleneck and classification head. We also adopt a synergistic domain alignment loss (SDAL), which combines cross-entropy (CE) and maximum mean discrepancy (MMD) to promote both discriminative learning and cross-domain alignment. Experimental results on Office-Home, Office-31, VisDA-2017, and DomainNet demonstrate that EUDA achieves competitive performance across diverse domain complexities, while reducing the number of trainable parameters by 42 to 99.7%. These results show the suitability of the proposed method for resource-constrained and distributed environments.
Unsupervised domain adaptation (UDA) based on large vision-language models (VLMs) has recently demonstrated strong generalization ability, yet it remains fundamentally challenged by noisy pseudo-labels and inefficient adaptation under large domain shifts. In this paper, we propose Progressive Hybrid Pseudo-Labeling for UDA with Ascending Low-Rank Adaptation (termed as PHPL), a parameter-efficient paradigm that addresses these challenges from two complementary perspectives. 1) We introduce a progressive hybrid pseudo-labeling strategy that constructs target-domain supervision by fusing predictions from a frozen teacher model and an adaptive student model with a progressive weighting scheme. By gradually transferring predictive responsibility from the teacher to the student during training, PHPL effectively mitigates early-stage pseudo-label noise and stabilizes self-training under large domain shifts. 2) To enable efficient and stable adaptation of large VLMs, we propose an ascending low-rank adaptation strategy that allocates LoRA capacity in a depth-aware manner. Specifically, larger low-rank updates are assigned to deeper, semantically richer layers, while shallow layers remain lightly parameterized, striking a favorable balance between parameter efficiency and representational expressiveness. We conduct extensive experiments on five widely-used UDA benchmarks, including Office-Home, Office-31, VisDA-2017, Mini-DomainNet, and DomainNet. Experimental results verify that PHPL consistently achieves higher performance across various cross-domain scenarios compared with existing CNN, Transformer, and VLMs-based solutions. Notably, PHPL demonstrates strong robustness on highly challenging large-scale conditions while requiring significantly less computational overhead, validating the effectiveness and scalability of the proposed lightweight adaptation paradigm. The code is available at https://github.com/el2k/PHPL
Yangtao Wang, Mingxin Huang, Xingwei Deng et al.· IEEE Transactions on Image P...· 0 citations
Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well on a related unlabeled target domain. They generally introduce an auxiliary adaptation-related task that can be integrated into the multitask paradigm, which aims to merge multiple single-task models into a unified architecture. In this paper, we propose to associate domain adaptation and multitask balancing in the realistic context of an extreme class imbalance. Therefore, we propose a combined framework to cover and validate these approaches, and evaluate its performance in the physics-based context of the Cherenkov Telescope Array Observatory (CTAO). Along with a comparative study of some relevant adaptation techniques, we highlight the impact of extreme label shift and extend the investigations on importance weighting to rectify it. The complete code and results are published and available as open-source resources on Zenodo.
M. Dell'aiera, Thomas Vuillaume, Alexandre Benoit· Astronomy and Computing· 1 citation
Active Domain Adaptation (ADA) enhances transfer learning by selecting the most informative samples from the target domain for annotation. The source-free variant, ASFDA, operates using only a pre-trained source model and unlabeled target data. However, existing approaches typically assume that distribution shift arises solely from changes in the feature or label distribution, thereby neglecting concept shift (the divergence of $p(y|x)$ across domains). In this paper, we propose ADA-CS, a plug-and-play module compatible with any ADA or ASFDA framework. Without requiring access to source data, ADA-CS isolates concept shift from other forms of shifts. The concept shift severity is quantified to prioritize samples exhibiting the largest discrepancy in $p(y|x)$ for annotation. We further introduce a CSS metric to quantify the Concept Shift Severity across domains, revealing that non-negligible concept shift exists in many transfer tasks. Extensive experiments on four vision benchmarks (Office-31, Digits, DomainNet, and Office-Home RSUT) and one large-scale tabular dataset (USAccident) show that ADA-CS improves performance when combined with a wide range of active learning, ADA, and ASFDA strategies. Moreover, the rapid decline of CSS during adaptation provides direct evidence of our approach's effectiveness in identifying and correcting concept shift.
Unsupervised cross-domain image retrieval aims to retrieve semantically consistent images across domains with significant domain gaps, which poses substantial challenges under the absence of annotations in both domains. Existing approaches primarily rely on internally derived supervision signals for representation learning and cross-domain alignment. However, such internally induced supervision tends to impose an upper bound on achievable retrieval performance, as it lacks stable semantic references to support reliable category-level correspondence across domains. To address these limitations, we propose Selective Constraint Learning (SCL), a framework that introduces external semantic guidance as a stable prior for unsupervised cross-domain image retrieval. Leveraging a pre-trained foundation model, SCL constructs a dual-scope constraint bank to capture high-confidence positive and negative semantic relations within and across domains. Based on this, we design a generic constraint loss to jointly facilitate intra-domain compactness and inter-domain alignment. In addition, prototypical geometry regularization is designed to enhance in-domain structural stability through prototype-centered pull-and-push forces. Extensive experiments on multiple benchmarks demonstrate that SCL consistently outperforms state-of-the-art methods.
Wensi Fang, Xiaodan Zhang, Xiaoyu Lian et al.· Annual International ACM SIG...· 0 citations
3D unsupervised domain adaptive (UDA) segmentation mitigates the high cost of manual annotations of the new domain data. Self-training has emerged as the dominant approach in this area, where its success heavily depends on a well-initialized warm-up model to generate reliable pseudo labels. However, existing methods often depend on source supervision or output-level adversarial alignment to obtain the warm-up model, which suffer from limited generalization and training instability due to the large domain gap between domains. Constructing domain-similar representations is an effective way to bridge this gap. In this work, we propose CVKD-UDA, which revisits voxel size as a core design factor to construct domain-similar representations and leverages cross-view complementary cues to balance transferability and discriminability of the warm-up model. First, we generate two complementary views by varying voxel sizes and introduce a cross-view knowledge distillation (CVKD) to enhance generalization and target perception of the model. Second, to balance transferability and discriminability, we design a lightweight Decouple-Adapter and an auxiliary imitation classifier to decouple cross-view knowledge transfer. Extensive experiments on two benchmarks demonstrate that CVKD-UDA effectively improves the performance of self-training methods and provides a new perspective for 3D UDA segmentation. Our code will be available at GitHub.
Zhimin Yuan, Ming Cheng, Shangshu Yu et al.· IEEE transactions on multime...· 0 citations
Unified architectures that jointly perform semantic segmentation and monocular height estimation offer improved computational efficiency through shared representations, but face challenges in remote sensing applications: scarce annotations, intertask interference, and cross-regional domain shifts. These issues often lead to severe performance degradation, as models struggle with domain discrepancies and conflicting gradients. Moreover, existing domain adaptation methods remain constrained, suffering from low pseudolabel confidence, feature misalignment, and negative transfer. To address these, we propose DPCDO, a dynamic-coordinated learning approach for unsupervised multitask domain adaptation, which jointly models the multivariate conditional generation process of task outputs, domain alignment, and pseudolabel consistency. DPCDO integrates three synergistic modules: 1) dynamic patchwise prototype matching dynamically aligns local feature distributions to accommodate topographic diversity, promoting domain-invariant representation learning and cross-task information sharing; 2) multistream multiscale consistency constraint performs multiscale perturbations and enforces cross-stream consistency to enhance pseudolabel reliability; and 3) decoupled optimization for multitask heads to resolve intertask gradient conflicts. Extensive experiments show DPCDO consistently outperforms state-of-the-art methods in both semantic segmentation and monocular height estimation, validating its effectiveness in disentangling domain shifts and enhancing cross-task synergy.
Zitong Wu, Yaoyao Yin, Biao Hou et al.· IEEE Transactions on Geoscie...· 0 citations