Alignment-Aware Model Adaptation via Feedback-Guided Optimization
Department of Computer Science, University of British Columbia, Location, Canada（不列颠哥伦比亚大学计算机科学系）；Vector Institute of AI, Toronto, Canada（人工智能向量研究所）；Stony Brook University, New York, USA（石溪大学）
Gaurav Bhatt, Aditya Chinchure, Jiawei Zhou, Leonid Sigal
Fine-tuning is the primary mechanism for adapting foundation models to downstream tasks; however, standard approaches largely optimize task objectives in isolation and do not account for secondary yet critical alignment objectives (e.g., safety and hallucination avoidance). As a result, downstream fine-tuning can degrade alignment and fail to correct pre-existing misaligned behavior. We propose an alignment-aware fine-tuning framework that integrates feedback from an external alignment signal through policy-gradient-based regularization. Our method introduces an adaptive gating mechanism that dynamically balances supervised and alignment-driven gradients on a per-sample basis, prioritizing uncertain or misaligned cases while allowing well-aligned examples to follow standard supervised updates. The framework further learns abstention behavior for fully misaligned inputs, incorporating conservative responses directly into the fine-tuned model. Experiments on general and domain-specific instruction-tuning benchmarks demonstrate consistent reductions in harmful and hallucinated outputs without sacrificing downstream task performance. Additional analyses show robustness to adversarial fine-tuning, prompt-based attacks, and unsafe initializations, establishing adaptively gated alignment optimization as an effective approach for alignment-preserving and alignment-recovering model adaptation.
Recent advances in domain adaptation establish that requiring a low risk on the source domain and equal feature marginals degrade the adaptation's performance. At the same time, empirical evidence shows that incorporating an unsupervised target domain term that pushes decision boundaries away from the high-density regions, along with relaxed alignment, improves adaptation. In this paper, we theoretically justify such observations via a new bound on the target risk, and we connect two notions of relaxation for divergence, namely $β-$relaxed divergences and localization. This connection allows u…
Unsupervised domain adaptation leverages rich information from a labeled source domain to model an unlabeled target domain. Existing methods attempt to align the cross-domain distributions. However, the statistical representations of the alignment of the two domains are not well addressed. In this paper, we propose deep least squares alignment (DLSA) to estimate the distribution of the two domains in a latent space by parameterizing a linear model. We further develop marginal and conditional adaptation loss to reduce the domain discrepancy by minimizing the angle between fitting lines and inte…
WiFi Channel State Information (CSI)-based human activity recognition (HAR) provides a privacy-preserving, device-free sensing solution for smart environments. However, its deployment on edge devices is severely constrained by domain shift, where recognition performance deteriorates under varying environmental and hardware conditions. This study presents maxVSTAR (maximally adaptive Vision-guided Sensing Technology for Activity Recognition), a closed-loop, vision-guided model adaptation framework that autonomously mitigates domain shift for edge-deployed CSI sensing systems. The proposed syste…
The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source domain with identical label space is a challenging task. Partial domain adaptation alleviates this problem of procuring a labeled dataset with identical label space assumptions and addresses a more practical scenario where the source label set subsumes the target label set. This, however, presents a few additional obstacles during adaptation. Samples with categor…
Monash University（莫纳什大学）；VinUniversity（文莱大学）；University at Buffalo（布法罗大学）
Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that clinical narratives possess, which leads to unsatisfactory performance. In this paper, we present a simple yet effective hardness-guided domain adaptation (HGDA) framework for bioNER tasks that can effectively leverage the domain hardness information to improve the adaptability of the learnt model in low-resource scenarios. Experimental results on biomedical d…
In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly-confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discr…
Prognostics and Health Management (PHM) is an emerging field which has received much attention from the manufacturing industry because of the benefits and efficiencies it brings to the table. And Remaining Useful Life (RUL) prediction is at the heart of any PHM system. Most recent data-driven research demand substantial volumes of labelled training data before a performant model can be trained under the supervised learning paradigm. This is where Transfer Learning (TL) and Domain Adaptation (DA) methods step in and make it possible for us to generalize a supervised model to other domains with …
SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels
Saw Swee Hock School of Public Health, National University of Singapore（新加坡国立大学 Saw Swee Hock 公共卫生学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Guangzhou Research Translation and Innovation Institute, National University of Singapore（新加坡国立大学广州研究翻译与创新研究所）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Beijing Key Laboratory of Brainnetome and Brain-Computer Interface, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑网络与脑机接口重点实验室）；Brainnetome Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑网络中心）
Chongqing University（重庆大学）；School of Microelectronics and Communication Engineering（微电子与通信工程学院）
Unsupervised domain adaptation (UDA) aims to improve the classification performance on an unlabeled target domain by leveraging information from a fully labeled source domain. Recent approaches explore domain-invariant and class-discriminant representations to tackle this task. These methods, however, ignore the interaction between domain alignment learning and class discrimination learning. As a result, the missing or inadequate tradeoff between domain alignment and class discrimination are prone to the problem of negative transfer. In this paper, we propose Dynamic Weighted Learning (DWL) to…
Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment
Department of Mathematics and Statistics, Université de Montréal, Montreal, Canada（蒙特利尔大学数学与统计学系）；Mila - Quebec AI Institute, Montreal, Canada（魁北克人工智能研究所）；Department of Mathematics and Statistics, Utah State University, Logan, Utah, USA（犹他州立大学数学与统计学系）；Department of Statistics, Brigham Young University, Provo, Utah, USA（Brigham Young 大学统计学系）
Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. To learn such representations, domain adaptation frameworks usually include a domain invariant representation learning approach to measure and reduce the domain discrepancy, as well as a discriminator for classification. Inspired by Wass…
Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain. To mitigate these problems, we propose a novel discrepancy called source-guided discrepan…
Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversarial approaches consist of aligning source and target encodings, often motivating this approach as minimizing two (of three) terms in a theoretical bound on target error. Unfortunately, this minimization can cause arbitrary increases in the third term, e.g. they can break down un…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；MIT（麻省理工学院）
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}. It can be expensive or even infeasible to obtain required amount of labeled data in all possible domains. Unsupervised domain adaptation sets out to address this problem, aiming to learn a good predictive model for the target domain using labeled examples from the source domain but only unlabeled examples from the target domain. Domain alignment app…
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）；Aalto University（阿尔托大学）；NVIDIA（英伟达）
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data and the domain shift makes the predictions on the target data unreliable. We propose quantifying the uncertainty in the source model predictions and utilizing it to guide the target adaptation. For this, we construct a probabilistic source model by incorporating priors on the network parameters inducing a distribution over the model predictions. Uncertainties are estimated by employing a Laplace approximation and inco…
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as well. We propose a novel objective function that encourages the class-conditional distributions to have disjoint support in feature space. We further exploit adversarial regularization to improve the performance of the classifier on the domain for which no annotated data is availabl…
Aselsan Inc（阿瑟尔桑公司）；Middle East Technical University（中东技术大学）；NOROM Neuroscience and Neurotechnology Excellency Center（NOROM神经科学与神经技术卓越中心）
Deep models trained on large-scale RGB image datasets have shown tremendous success. It is important to apply such deep models to real-world problems. However, these models suffer from a performance bottleneck under illumination changes. Thermal IR cameras are more robust against such changes, and thus can be very useful for the real-world problems. In order to investigate efficacy of combining feature-rich visible spectrum and thermal image modalities, we propose an unsupervised domain adaptation method which does not require RGB-to-thermal image pairs. We employ large-scale RGB dataset MS-CO…
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the so…
Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free domain adaptation for semantic segmentation, wherein a source model must adapt itself to a new target domain given only unlabeled target data. We propose Augmentation Consistency-guided Self-training (AUGCO), a source-free adaptation algorithm that uses the model's pixel-level predictive consistency across diverse, automatically generated views of each target image along with mode…
Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China（电子科技大学基础与前沿研究院）
Domain adaptation (DA) is used for adaptively obtaining labels of an unprocessed data set with a given related, but different labelled data set. Subspace alignment (SA), a representative DA algorithm, attempts to find a linear transformation to align the subspaces of the two different data sets. The classifier trained on the aligned labelled data set can be transferred to the unlabelled data set to predict the target labels. In this paper, two quantum versions of the SA are proposed to implement the DA procedure on quantum devices. One method, the quantum subspace alignment algorithm (QSA), ac…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）
Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there are two significant challenges: (1) degenerated feature transformation, which means that distribution alignment is often performed in the original feature space, where feature distortions are hard to overcome. On the other hand, subspace learning is not sufficient to reduce the distribution divergence. (2) unevaluated distribution alignment, whi…
Duke University（杜克大学）；Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）；Microsoft Research（微软研究院）
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain features that are divergent from source-domain features. However, by optimizing via such domain classification discrepancy, ambiguous target samples that are not smoothly distributed on the low-dimensional data manifold are often missed. To solve this issue, we propose a novel Contra…
Although various image-based domain adaptation (DA) techniques have been proposed in recent years, domain shift in videos is still not well-explored. Most previous works only evaluate performance on small-scale datasets which are saturated. Therefore, we first propose a larger-scale dataset with larger domain discrepancy: UCF-HMDB_full. Second, we investigate different DA integration methods for videos, and show that simultaneously aligning and learning temporal dynamics achieves effective alignment even without sophisticated DA methods. Finally, we propose Temporal Attentive Adversarial Adapt…
Arizona State University（亚利桑那州立大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
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 …
We propose a novel manifold based geometric approach for learning unsupervised alignment of word embeddings between the source and the target languages. Our approach formulates the alignment learning problem as a domain adaptation problem over the manifold of doubly stochastic matrices. This viewpoint arises from the aim to align the second order information of the two language spaces. The rich geometry of the doubly stochastic manifold allows to employ efficient Riemannian conjugate gradient algorithm for the proposed formulation. Empirically, the proposed approach outperforms state-of-the-ar…
University of Electronic Science and Technology of China（电子科技大学）
Correlation alignment (CORAL), a representative domain adaptation (DA) algorithm, decorrelates and aligns a labelled source domain dataset to an unlabelled target domain dataset to minimize the domain shift such that a classifier can be applied to predict the target domain labels. In this paper, we implement the CORAL on quantum devices by two different methods. One method utilizes quantum basic linear algebra subroutines (QBLAS) to implement the CORAL with exponential speedup in the number and dimension of the given data samples. The other method is achieved through a variational hybrid quant…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to lack of source data, we cannot directly match the data distributions between domains unlike typical domain adaptation algorithms. To cope with this problem, we propose utilizing batch normalization statistics stored in the pretrained model to approximate the distribution of unobserved source data. Specifically, we fix the classifier part of the model during a…
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to enforce the class-level distribution alignment across the source and target domains. These methods, however, are vulnerable to the error accumulation and thus incapable of preserving cross-domain category consistency, as the pseudo-labeling accuracy is not guaranteed explicitly. In this paper, we propose the Progressive Feature Alignment Network (PFAN) to align t…
JD AI Research（京东人工智能研究院）；University of Science and Technology of China（中国科学技术大学）；Nanjing University（南京大学）
Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the classifier in the target domain are two widely used objectives. Existing methods often separately optimize these two individual objectives, which makes them suffer from the neglect of the other. However, optimizing these two aspects together is not trivial. To alleviate the above issues, we propose a novel method that jointly optimizes semantic domain alignment and…
Arizona State University（亚利桑那州立大学）；Lawrence Livermore National Labs（劳伦斯利弗莫尔国家实验室）
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and (b) aligning the source and target domains. Traditionally, these tasks have either been considered as separate, or assumed to be implicitly addressed together with high-capacity feature extractors. When considered separately, alignment is usually viewed as a problem of aligning data distributions, either through geometric approaches such as subspace alignmen…
Arizona State University（亚利桑那州立大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their mathematical elegance and tractability, these methods are often found to be ineffective at producing domain-invariant features with complex, real-world datasets. Motivated by the recent advances in representation learning with deep networks, this paper revisits the use of subspace alignment for UDA and proposes a novel adaptation algorithm that consistently …
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift. Target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate th…
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学电气与电子工程学院）；School of Computer Science and Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学计算机科学与工程学院）
Samsung SDS Technology Research（三星SDS技术研究院）；Seoul National University of Science and Technology（首尔国立科技大学）
Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices. Some recently developed approaches do not require source images during adaptation, but they show limited performance on perturbed images. To address these problems, we propose a novel source-free UDA method that uses only a pre-trained source model and unlabeled target images. Our method captures the aleatoric uncertainty by incorporating data augmentation …
Addressing shifts in data distributions is an important prerequisite for the deployment of deep learning models to real-world settings. A general approach to this problem involves the adjustment of models to a new domain through transfer learning. However, in many cases, this is not applicable in a post-hoc manner to deployed models and further parameter adjustments jeopardize safety certifications that were established beforehand. In such a context, we propose to deal with changes in the data distribution via guided data homogenization which shifts the burden of adaptation from the model to t…
Annotating objects with 3D bounding boxes in LiDAR pointclouds is a costly human driven process in an autonomous driving perception system. In this paper, we present a method to semi-automatically annotate real-world pointclouds collected by deployment vehicles using simulated data. We train a 3D object detector model on labeled simulated data from CARLA jointly with real world pointclouds from our target vehicle. The supervised object detection loss is augmented with a CORAL loss term to reduce the distance between labeled simulated and unlabeled real pointcloud feature representations. The g…
University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；Boston University（波士顿大学）
Deep neural networks are able to learn powerful representations from large quantities of labeled input data, however they cannot always generalize well across changes in input distributions. Domain adaptation algorithms have been proposed to compensate for the degradation in performance due to domain shift. In this paper, we address the case when the target domain is unlabeled, requiring unsupervised adaptation. CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation. Here,…
Joint Distribution Alignment for Universal Domain Adaptation
School of Software Engineering, South China University of Technology（华南理工大学软件工程学院）；School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；College of Computer Science, Chongqing University（重庆大学计算机学院）
