Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the amount of data required, we propose a new method for transferring prior knowledge of the pre-trained generator, which is trained with a large dataset, to a small dataset in a different domain. Using such prior knowledge, the model can generate images leveraging some common sense that cannot be acquired from a small dataset. In this work, we propose a novel method focusing on the parameters for batch statistics, scale and shift, of the hidden layers in the generator. By training only these parameters in a supervised manner, we achieved stable training of the generator, and our method can generate higher quality images compared to previous methods without collapsing, even when the dataset is small (~100). Our results show that the diversity of the filters acquired in the pre-trained generator is important for the performance on the target domain. Our method makes it possible to add a new class or domain to a pre-trained generator without disturbing the performance on the original domain.
Mila；Université de Montréal（蒙特利尔大学）；Imperial College London（帝国理工学院）；Microsoft Research（微软研究院）
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes between source and target distributions. However, these models do not perform well when the modes are not well-matched, as would be the case when samples are drawn independently from two different, but related, domains. This mode imbalance is problematic as generative adversarial …
Qualcomm Technologies, Inc.（高通技术公司）；Qualcomm AI Research（高通人工智能研究院）；KAIST（韩国科学技术院）
This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., transductive batch normalization (TBN), which calculates the mean and the variance from the current test batch rather than using the running mean and variance obtained from the source data, i.e., conventional batch normalization (CBN). Adopting TBN that employs test batch statistics mitigates the performance degradation caused by the domain shift. However, re-estimating normalization statistics using test data depends on …
University of Southern California（南加州大学）；Facebook AI
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples. Known as Test-Time Adaptation, most prior works studying this task follow two assumptions in their evaluation where (1) test samples come together as a large batch, and (2) all from a single test distribution. However, in practice, these two assumptions may not stand, the reasons for which we propose two new evaluation settings where batch sizes are arbitrary and multiple distributions are considered. Unlike the previous methods that require a large…
Institute of Computing Technology, Chinese Academy of Sciences（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）；Peng Cheng Laboratory（鹏城实验室）；Huawei Technologies（华为技术有限公司）
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain. A common solution is to minimize the Shannon Entropy to push the decision boundary away from the high density area. However, entropy minimization also leads to severe reduction of prediction diversity, and unfortunately brings harm to the domain adaptation. In this paper, we investigate the prediction discriminability and diversity by studying the structure of the classification output matrix of a randomly selected …
Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with large-scale or dynamic data sources, data from a defined domain is not usually available all at once. For instance, in a streaming data scenario, dataset statistics effectively become a function of time. We introduce a framework for adaptation over non-stationary distribution shifts applicable to large-scale and streaming data scenarios. The model is adapted se…
In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain representations". Previous UDA approaches for semantic segmentation either employed simultaneous training of the model in the source and target domains, or they relied on an additional network, replaying source domain knowledge to the model during adaptation. In contrast, we present our novel Unsupervised BatchNorm Adaptation (UBNA) method, which adapts a given pre-trained model to an unseen target domain without using …
Technische Universität Braunschweig（布伦瑞克工业大学）；Institute of Communications Technology（通信技术研究所）
Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is addressed by unsupervised domain adaptation (UDA) approaches trained either simultaneously on source and target domain datasets or even source-free only on target data in an offline fashion. In this work, we further expand a source-free UDA approach to a continual and therefore online-capable UDA on a single-image basis for semantic segmentation. Accordingly…
Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity
Machine Learning and Vision Lab（机器学习与视觉实验室）；Indian Institute of Technology Hyderabad（印度理工学院海得拉巴学院）；Department of Computer Science and Engineering（计算机科学与工程系）
Blue Well 8, LLC（Blue Well 8有限责任公司）；Pioneer Square Labs（先锋广场实验室）
Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax activation, results in improved generalization across visual data domains in a refined ResNet model. The approach adds negligible computational complexity yet outperforms many domain adaptation methods that explicitly learn to align data domains. We benchmark this technique on the Office-Home dataset and show that batch normalization is competitive with other leadi…
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…
In recent years, unsupervised domain adaptation (UDA) for semantic segmentation has brought many researchers'attention. Many of them take an approach to design a complex system so as to better align the gap between source and target domain. Instead, we focus on the very basic structure of the deep neural network, Batch Normalization, and propose to replace the Sharing Affine Transformation with our proposed Separate Affine Transformation (SEAT). The proposed SEAT is simple, easily implemented and easy to integrate into existing adversarial learning based UDA methods. Also, to further improve t…
Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called A…
Domain Adaptation (DA) techniques are important for overcoming the domain shift between the source domain used for training and the target domain where testing takes place. However, current DA methods assume that the entire target domain is available during adaptation, which may not hold in practice. This paper considers a more realistic scenario, where target data become available in smaller batches and adaptation on the entire target domain is not feasible. In our work, we introduce a new, data-constrained DA paradigm where unlabeled target samples are received in batches and adaptation is p…
Virginia Tech（弗吉尼亚理工大学）；Google Cloud AI（谷歌云人工智能）；Google Brain（谷歌大脑）；University of Maryland, College Park（马里兰大学帕克分校）
We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchNorm (statistics) calibration. Our approach has two core components. First, we replace the manually designed BatchNorm calibration rule with a learnable module. Second, we leverage strong data augmentation to simulate random domain shifts for learning the calibration rule. In contrast to existing domain adaptation methods, our method does not require accessing the target domain data at tra…
Google Research（谷歌研究院）；IISc Bangalore（印度科学学院班加罗尔分院）；Stanford University（斯坦福大学）；IIT Kanpur（印度理工学院坎普尔分校）
In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially, TTA assumes no access to the source data or even any additional labeled/unlabeled samples from the target distribution to finetune the source model. In this work, we consider TTA in a more pragmatic setting which we refer to as SITA (Single Image Test-time Adaptation). Here, when making a prediction, the model has access only to the given single test instance, rather than a batch of instances, as typically been cons…
Current deep learning adaptive optimizer methods adjust the step magnitude of parameter updates by altering the effective learning rate used by each parameter. Motivated by the known inverse relation between batch size and learning rate on update step magnitudes, we introduce a novel training procedure that dynamically decides the dimension and the composition of the current update step. Our procedure, Dynamic Batch Adaptation (DBA) analyzes the gradients of every sample and selects the subset that best improves certain metrics such as gradient variance for each layer of the network. We presen…
pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data
Center for Computational & Data Sciences (CCDS)（计算与数据科学中心）；Independent University（独立大学）；University of Central Florida（中央佛罗里达大学）；Curtin University（Curtin大学）；Umeå University（乌梅拉大学）
Graz University of Technology（格拉茨技术大学）；Christian Doppler Laboratory for Embedded Machine Learning（克里斯蒂安·多普勒嵌入式机器学习实验室）
Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we mod…
Nanjing University of Science and Technology（南京理工大学）；University of Trento（特伦托大学）；Huawei Technologies Ireland（华为技术爱尔兰公司）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, we propose a novel Online Meta-Learning model with Adaption (OMLA). Our proposal is based on two main contributions. First, to reducethe domain-shift between source and target feature distributions we introduce an online feature alignment procedurederived from Batch Normalization. Second, we devise a meta-learning approach that exploits feat…
Batch normalization (BN) allows training very deep networks by normalizing activations by mini-batch sample statistics which renders BN unstable for small batch sizes. Current small-batch solutions such as Instance Norm, Layer Norm, and Group Norm use channel statistics which can be computed even for a single sample. Such methods are less stable than BN as they critically depend on the statistics of a single input sample. To address this problem, we propose a normalization of activation without sample statistics. We present WeightAlign: a method that normalizes the weights by the mean and scal…
University of Electronic Science and Technology of China（电子科技大学）；Zhejiang University（浙江大学）
Deep neural networks have a clear degradation when applying to the unseen environment due to the covariate shift. Conventional approaches like domain adaptation requires the pre-collected target data for iterative training, which is impractical in real-world applications. In this paper, we propose to adapt the deep models to the novel environment during inference. An previous solution is test time normalization, which substitutes the source statistics in BN layers with the target batch statistics. However, we show that test time normalization may potentially deteriorate the discriminative stru…
Deep networks have been used to learn transferable representations for domain adaptation. Existing deep domain adaptation methods systematically employ popular hand-crafted networks designed specifically for image-classification tasks, leading to sub-optimal domain adaptation performance. In this paper, we present Neural Architecture Search for Domain Adaptation (NASDA), a principle framework that leverages differentiable neural architecture search to derive the optimal network architecture for domain adaptation task. NASDA is designed with two novel training strategies: neural architecture se…
ConvLoRA and AdaBN based Domain Adaptation via Self-Training
SFI Research Centre for Machine Learning, Dublin City University（都柏林城市大学SFI机器学习研究中心）；Insight SFI Research Centre for Data Analytics, Dublin City University（都柏林城市大学Insight SFI数据分析研究中心）；School of Computing, Dublin City University（都柏林城市大学计算机学院）
Tongji University（同济大学）；New Jersey Institute of Technology（新泽西理工学院）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）；Fudan University（复旦大学）
Typical adversarial-training-based unsupervised domain adaptation methods are vulnerable when the source and target datasets are highly-complex or exhibit a large discrepancy between their data distributions. Recently, several Lipschitz-constraint-based methods have been explored. The satisfaction of Lipschitz continuity guarantees a remarkable performance on a target domain. However, they lack a mathematical analysis of why a Lipschitz constraint is beneficial to unsupervised domain adaptation and usually perform poorly on large-scale datasets. In this paper, we take the principle of utilizin…
Tel Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）
We study the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of the shared classes. The score is used to select which samples in the target domain to pseudo-label during training. Another loss term encourages diversity of labels within each batch. Taken together, our method is shown to outperform, by a sizable margin, the current state of the art on the literature benchmarks.
Korea Advanced Institute of Science Technology (KAIST)（韩国科学技术院）
The performance of DNNs trained on clean images has been shown to decrease when the test images have common corruptions. In this work, we interpret corruption robustness as a domain shift and propose to rectify batch normalization (BN) statistics for improving model robustness. This is motivated by perceiving the shift from the clean domain to the corruption domain as a style shift that is represented by the BN statistics. We find that simply estimating and adapting the BN statistics on a few (32 for instance) representation samples, without retraining the model, improves the corruption robust…
Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
South China University of Technology（华南理工大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究所）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）
In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without labels. The existing literature mostly operates on artificial shifts obtained via adversarial perturbations of a test image. Motivated by this, we evaluate the state of the art on two realistic and challenging sources of domain shifts, namely contextual and semantic shifts. Contextual shifts correspond to the environment types, for example, a model pre-trained on indoor context has to adapt to the outdoor context on…
Batch Normalization (BN) is one of the most widely used techniques in Deep Learning field. But its performance can awfully degrade with insufficient batch size. This weakness limits the usage of BN on many computer vision tasks like detection or segmentation, where batch size is usually small due to the constraint of memory consumption. Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption. In this paper, we reve…
Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究所）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data to mitigate such performance degradation. Although such methods can adapt on-the-fly without first collecting a large target domain dataset, their performance is dependent on streaming conditions such as mini-batch size and class-distribution, which can be unpredictable in practice. In this work, we propo…
Google Research（谷歌研究院）；University of Maryland, College Park（马里兰大学帕克分校）
Batch normalization (BN) has been very effective for deep learning and is widely used. However, when training with small minibatches, models using BN exhibit a significant degradation in performance. In this paper we study this peculiar behavior of BN to gain a better understanding of the problem, and identify a cause. We propose 'EvalNorm' to address the issue by estimating corrected normalization statistics to use for BN during evaluation. EvalNorm supports online estimation of the corrected statistics while the model is being trained, and does not affect the training scheme of the model. As…
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into low dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously. The objective function can be solved efficiently in a closed form. Extensive experiments have verified that the…
Patch-aware Batch Normalization for Improving Cross-domain Robustness
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
University of Kentucky（肯塔基大学）；Eastern Kentucky University（东肯塔基大学）
Most research on domain adaptation has focused on the purely unsupervised setting, where no labeled examples in the target domain are available. However, in many real-world scenarios, a small amount of labeled target data is available and can be used to improve adaptation. We address this semi-supervised setting and propose to use dynamic feature alignment to address both inter- and intra-domain discrepancy. Unlike previous approaches, which attempt to align source and target features within a mini-batch, we propose to align the target features to a set of dynamically updated class prototypes,…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably estimated from it during a training iteration. To address this problem, we present Cross-Iteration Batch Normalization (CBN), in which examples from multiple recent iterations are jointly utilized to enhance estimation quality. A challenge of computing statistics over multiple iterations is that the network activations from different iterations are not compar…
Univ Lyon（里昂大学）；Ecole Centrale de Lyon（里昂中央理工学院）；CNRS（法国国家科学研究中心）；INSA Lyon（里昂国立应用科学学院）；Univ Claude Bernard Lyon 1（里昂第一大学克洛德·贝尔纳）；Univ Louis Lumière Lyon 2（里昂第二大学路易·卢米埃尔）；Thales LAS France（泰雷兹LAS法国公司）
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we argue that, to reach further improvements, these approaches should be combined with training procedure modifications aiming to learn a more diverse set of patterns. Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned wi…
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation. From an augmented view of an image, BYOL trains an online network to predict a target network representation of a different augmented view of the same image. Unlike contrastive methods, BYOL does not explicitly use a repulsion term built from negative pairs in its training objective. Yet, it avoids collapse to a trivial, constant representation. Thus, it has recently been hypothesized that batch normalization (BN) is critical to prevent collapse in BYOL. Indeed, BN flows gradients across batch ele…
