Machine learning systems must adapt to data distributions that evolve over time, in applications ranging from sensor networks and self-driving car perception modules to brain-machine interfaces. We consider gradual domain adaptation, where the goal is to adapt an initial classifier trained on a source domain given only unlabeled data that shifts gradually in distribution towards a target domain. We prove the first non-vacuous upper bound on the error of self-training with gradual shifts, under settings where directly adapting to the target domain can result in unbounded error. The theoretical analysis leads to algorithmic insights, highlighting that regularization and label sharpening are essential even when we have infinite data, and suggesting that self-training works particularly well for shifts with small Wasserstein-infinity distance. Leveraging the gradual shift structure leads to higher accuracies on a rotating MNIST dataset and a realistic Portraits dataset.
The Graduate University for Advanced Studies (SOKENDAI)（综合研究大学院大学（SOKENDAI））；The Institute of Statistical Mathematics（统计数学研究所）；RIKEN（理化学研究所）
In domain adaptation, when there is a large distance between the source and target domains, the prediction performance will degrade. Gradual domain adaptation is one of the solutions to such an issue, assuming that we have access to intermediate domains, which shift gradually from the source to the target domain. In previous works, it was assumed that the number of samples in the intermediate domains was sufficiently large; hence, self-training was possible without the need for labeled data. If the number of accessible intermediate domains is restricted, the distances between domains become la…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
The vast majority of existing algorithms for unsupervised domain adaptation (UDA) focus on adapting from a labeled source domain to an unlabeled target domain directly in a one-off way. Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones. Under certain assumptions, Kumar et al. (2020) proposed a simple algorithm, Gradual Self-Training, along with a generalization bound in the order of $e^{O(T)} \left(\varepsi…
Hong Kong Polytechnic University（香港理工大学）；South China University of Technology（华南理工大学）
Domain adaptation becomes more challenging with increasing gaps between source and target domains. Motivated from an empirical analysis on the reliability of labeled source data for the use of distancing target domains, we propose self-training of auxiliary models (AuxSelfTrain) that learns models for intermediate domains and gradually combats the distancing shifts across domains. We introduce evolving intermediate domains as combinations of decreasing proportion of source data and increasing proportion of target data, which are sampled to minimize the domain distance between consecutive domai…
Faculty of Science and Technology, University of Macau（澳门大学科学与技术学院）；PolyU Academy for Artificial Intelligence, Hong Kong Polytechnic University（香港理工大学人工智能学院）
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tsinghua University（清华大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
The phenomenon of data distribution evolving over time has been observed in a range of applications, calling the needs of adaptive learning algorithms. We thus study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory, and we aim to learn a classifier on a target data distribution of interest. Under this setting, we provide the first generalization upper bound on the learning error under mild assumptions. Our results are algorithm agnostic, general for a range of loss functions, and only depend li…
The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaptation (GDA) is one promising way to mitigate such an issue, by leveraging additional unlabeled data that gradually shift from the source to the target. Through sequentially adapting the model along the "indexed" intermediate domains, GDA substantially improves the overall adaptation performance. In practice, however, the extra unlabeled data may not be separated into intermediate domains and indexed properly, limiting the applicability of GDA…
We focus on the problem of domain adaptation when the goal is shifting the model towards the target distribution, rather than learning domain invariant representations. It has been shown that under the following two assumptions: (a) access to samples from intermediate distributions, and (b) samples being annotated with the amount of change from the source distribution, self-training can be successfully applied on gradually shifted samples to adapt the model toward the target distribution. We hypothesize having (a) is enough to enable iterative self-training to slowly adapt the model to the tar…
Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Zhenguan AI Lab；Southwest Jiaotong University（西南交通大学）；Shanghai University（上海大学）；New Jersey Institute of Technology（新泽西理工学院）
Nanjing University of Aeronautics & Astronautics（南京航空航天大学）
Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target domain by transferring knowledge from labeled source domain with domain shift. Most of the existing UDA methods try to mitigate the adverse impact induced by the shift via reducing domain discrepancy. However, such approaches easily suffer a notorious mode collapse issue due to the lack of labels in target domain. Naturally, one of the effective ways to mitigate this issue is to reliably estimate the pseudo labels for target domain, which itself is hard. To overcome this, we propose a novel UDA method named Progressive Adap…
Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential data). The underlying idea of deep domain adaptation is to bridge the gap between source and target domains in a joint space so that a supervised classifier trained on labeled source data can be nicely transferred to the target domain. This idea is certainly intuitive and powerful, however, limited theoretical understandings have been developed to support its underpinning princi…
Joint scene understanding and segmentation for automotive applications is a challenging problem in two key aspects:- (1) classifying every pixel in the entire scene and (2) performing this task under unstable weather and illumination changes (e.g. foggy weather), which results in poor outdoor scene visibility. This poor outdoor scene visibility leads to a non-optimal performance of deep convolutional neural network-based scene understanding and segmentation. In this paper, we propose an efficient end-to-end contemporary automotive semantic scene understanding approach under foggy weather condi…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
Domain adaptation is essential to enable wide usage of deep learning based networks trained using large labeled datasets. Adversarial learning based techniques have shown their utility towards solving this problem using a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate, it would be useful if a distribution based discriminator could be used to bridge this gap. This could be achieved using multiple classifiers or using traditional ensemble methods. In contrast, we suggest that a Monte Carlo dropout based ensem…
We consider a setting that a model needs to adapt to a new domain under distribution shifts, given that only unlabeled test samples from the new domain are accessible at test time. A common idea in most of the related works is constructing pseudo-labels for the unlabeled test samples and applying gradient descent (GD) to a loss function with the pseudo-labels. Recently, \cite{GSRK22} propose conjugate labels, which is a new kind of pseudo-labels for self-training at test time. They empirically show that the conjugate label outperforms other ways of pseudo-labeling on many domain adaptation ben…
Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem. The proposed STN not only aligns the discriminative directions of domains but also matches both the marginal and conditional distributions across domains. To circumvent negative transfer, STN aligns the conditional distributions by using the soft-label …
Technical Report for ICCV 2023 Visual Continual Learning Challenge: Continuous Test-time Adaptation for Semantic Segmentation
Poznań University of Technology（波兹南理工大学）；IDEAS NCBR（IDEAS国家计算智能研究中心）；Shenyang Institute of Automation（沈阳自动化研究所）；Chinese Academy of Sciences（中国科学院）；Computer Vision Center（计算机视觉中心）；Autonomous University of Barcelona（巴塞罗那自治大学）；Gdańsk University of Technology（格但斯克理工大学）
Carleton University（卡尔顿大学）；CIFAR AI Chair（CIFAR人工智能讲席）；Amii（阿尔伯塔机器智能研究所）
Unsupervised domain adaptation reduces the reliance on data annotation in deep learning by adapting knowledge from a source to a target domain. For privacy and efficiency concerns, source-free domain adaptation extends unsupervised domain adaptation by adapting a pre-trained source model to an unlabeled target domain without accessing the source data. However, most existing source-free domain adaptation methods to date focus on the transductive setting, where the target training set is also the testing set. In this paper, we address source-free domain adaptation in the more realistic inductive…
Huawei Technologies Canada Co., Ltd（华为技术加拿大有限公司）；University of British Columbia（不列颠哥伦比亚大学）；Huawei Cloud（华为云）
This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD). To overcome the challenging issues of domain shift and pseudo-label noise, our method integrates a novel domain-centric augmentation method, a gradual self-labeling adaptation procedure, and a teacher-guided fine-tuning mechanism. Using our method, target domain samples can be leveraged to adapt object detection models without changing the model architecture or generating synthetic data. When applied to image corruptions and high-level cross-domain adaptation benchmarks, our method o…
University of Central Florida（中佛罗里达大学）；University of Macau（澳门大学）；Nanjing University（南京大学）
In many scenarios, 1) data streams are generated in real time; 2) labeled data are expensive and only limited labels are available in the beginning; 3) real-world data is not always i.i.d. and data drift over time gradually; 4) the storage of historical streams is limited and model updating can only be achieved based on a very short lookback window. This learning setting limits the applicability and availability of many Machine Learning (ML) algorithms. We generalize the learning task under such setting as a semi-supervised drifted stream learning with short lookback problem (SDSL). SDSL impos…
Contrastive Domain Adaptation for Time-Series via Temporal Mixup
Nanyang Technological University（南洋理工大学）；Agency for Science, Technology and Research（新加坡科技研究局）；Centre for Frontier AI Research（前沿人工智能研究中心）；Institute for Infocomm Research（资讯通信研究院）
University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Group（阿里巴巴集团）；Peng Cheng Laboratory（鹏城实验室）
In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem. Existing methods apply different kinds of priors or directly minimize the domain discrepancy to address this problem, which lack flexibility in handling real-world situations. Another research pipeline expresses the domain-specific information as a gradual transferring process, which tends to be suboptimal in accurately removing the domain-specific properties. In this paper, we address the modeling of domain-invariant and domain-specific informatio…
Tulane University（杜兰大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；IBM Research（IBM研究院）
Unsupervised domain adaptation (UDA) enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs from that of the target. However, UDA is not always successful and several accounts of `negative transfer' have been reported in the literature. In this work, we prove a simple lower bound on the target domain error that complements the existing upper bound. Our bound shows the insufficiency of minimizing source domain error and marginal distribution mismatch for a guaranteed reduction in the target domain error, due t…
Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School（戈登医学影像中心，麻省总医院与哈佛医学院）；Ewha Womans University（梨花女子大学）；University of Southern California（南加州大学）
Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain. The training of conventional solutions usually relies on the existence of both source and target domain data. However, privacy of the large-scale and well-labeled data in the source domain and trained model parameters can become the major concern of cross center/domain collaborations. In this work, to address this, we propose a practical solution to UDA for segmentation with a black-box segmentation mod…
Carnegie Mellon University（卡内基梅隆大学）；NVIDIA（英伟达）；General Motors R & D（通用汽车研发中心）
Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled training/source data and unseen test/target data exists. In particular, such difference is often referred to as `domain gap', and could cause significantly decreased performance which cannot be easily remedied by further increasing the representation power. Unsupervised domain adaptation (UDA) seeks to overcome such problem without target domain labels. In this paper, w…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
Adaptation of a classifier to new domains is one of the challenging problems in machine learning. This has been addressed using many deep and non-deep learning based methods. Among the methodologies used, that of adversarial learning is widely applied to solve many deep learning problems along with domain adaptation. These methods are based on a discriminator that ensures source and target distributions are close. However, here we suggest that rather than using a point estimate obtaining by a single discriminator, it would be useful if a distribution based on ensembles of discriminators could …
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Shanghai Key Laboratory of Digital Media Processing and Transmission（上海市数字媒体处理与传输重点实验室）
By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial learning. As an enhancement, category alignment is involved during adaptation to reinforce target feature discrimination by utilizing model prediction. However, there remain unexplored problems about pseudo-label inaccuracy incurred by wrong category predictions on target domain, and distribution deviation caused by overfitting on source domain. In this paper, w…
Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
School of Mathematics, Sun Yat-Sen University（中山大学数学学院）；School of Statistics and Mathematics, Guangdong University of Finance and Economics（广东财经大学统计与数学学院）；School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机学院）
National University of Singapore（新加坡国立大学）；Beijing Institute of Technology（北京理工大学）；Zhejing University（浙江大学）
Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models. However, we find that contemporary domain adaptation methods for cross-domain image understanding perform poorly when source domain is noisy. Weakly Supervised Domain Adaptation (WSDA) studies the domain adaptation problem under the scenario where sour…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
Unsupervised domain adaptation (UDA) has been a vital protocol for migrating information learned from a labeled source domain to facilitate the implementation in an unlabeled heterogeneous target domain. Although UDA is typically jointly trained on data from both domains, accessing the labeled source domain data is often restricted, due to concerns over patient data privacy or intellectual property. To sidestep this, we propose "off-the-shelf (OS)" UDA (OSUDA), aimed at image segmentation, by adapting an OS segmentor trained in a source domain to a target domain, in the absence of source domai…
Curriculum Reinforcement Learning (CRL) aims to create a sequence of tasks, starting from easy ones and gradually learning towards difficult tasks. In this work, we focus on the idea of framing CRL as interpolations between a source (auxiliary) and a target task distribution. Although existing studies have shown the great potential of this idea, it remains unclear how to formally quantify and generate the movement between task distributions. Inspired by the insights from gradual domain adaptation in semi-supervised learning, we create a natural curriculum by breaking down the potentially large…
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the training distribution shifts, the network is slow to adapt, and when it does adapt, it typically performs badly on the training distribution before the shift. Our method, Memory-based Parameter Adaptation, stores examples in memory and then uses a context-based lookup to directly modify the weights of a neural network. Much higher learning rates can be used fo…
