Recent research in geospatial machine learning demonstrates that models pretrained with self-supervised learning on Earth observation data can perform well on downstream tasks with limited labeled data. However, most benchmark datasets have few data modalities and poor global representation, limiting the ability to evaluate multimodal pretrained models at global scales. In order to fill this gap, we introduce MMEarth-Bench, a collection of five new environmental tasks with 12 modalities, globally distributed data, and both random and geographic test splits. We benchmark a diverse set of pretrained models and find that while (multimodal) pretraining tends to improve model robustness in limited data settings, geographic generalization abilities remain poor. Moreover, a simple randomly initialized multimodal model is competitive given enough labeled data. Although data is abundant, models can currently only make use of the modalities on which they were pretrained. To solve this problem, we propose using all the modalities available at test time as auxiliary tasks for test-time adaptation. Our model-agnostic method for test-time training with multimodal reconstruction (TTT-MMR) can improve performance across all models and tasks on both test splits. Furthermore, geographic batching leads to a good trade-off between regularization and specialization during TTT, which is especially beneficial for long-tail distributions. Our dataset, code, and visualization tool are linked on the project page: lgordon99.github.io/mmearth-bench.
While deep learning has led to significant advances in visual recognition over the past few years, such advances often require a lot of annotated data. Unsupervised domain adaptation has emerged as an alternative approach that does not require as much annotated data, prior evaluations of domain adaptation approaches have been limited to relatively similar datasets, e.g source and target domains are samples captured by different cameras. A new data suite is proposed that comprehensively evaluates cross-modality domain adaptation problems. This work pushes the limit of unsupervised domain adapta…
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；LIVIA ETS Montreal, ILLS International Laboratory on Learning Systems (ILLS)（蒙特利尔LIVIA ETS，学习系统国际实验室（ILLS））；Tulane University（路易斯安那州立大学）；Nanyang Technological University（南洋理工大学）；Hanyang University（翰阳大学）
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空航天信息研究所）；International Research Center of Big Data for Sustainable Development Goals（可持续发展目标大数据国际研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；The Department of Geomatics Engineering, Changsha University of Science and Technology（长沙理工大学测绘工程系）；The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）
In recent years, several efforts have been aimed at improving the robustness of vision models to domains and environments unseen during training. An important practical problem pertains to models deployed in a new geography that is under-represented in the training dataset, posing a direct challenge to fair and inclusive computer vision. In this paper, we study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation containing benchmarks across diverse tasks like scene recognition (GeoPlaces), image clas…
Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）；Centre for Frontier AI Research, A*STAR（A*STAR前沿人工智能研究中心）
Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic data can be used to train and adapt models to real world images without requiring their annotations. Recent UDA methods applies self-learning by training on pixel-wise classification loss using a student and teacher network. In this paper, we propose the addition of a consistency regularization term to semi-supervised UDA by modelling the inter-pixel relationship between el…
Centre for Artificial Intelligence, University of Technology Sydney（悉尼科技大学人工智能中心）
We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the intra-domain knowledge and inherent uncertainty learned by the network are under-explored. In this paper, we propose an orthogonal method, called memory regularization in vivo to exploit the intra-domain knowledge and regularize the model training. Specifically, we refer to the segmentation model itself as the memory module, and minor the discrepancy of the two class…
Beijing University of Posts and Telecommunications（北京邮电大学）
In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more, the model can be ruined due to the domain shift between training data and testing data. Text recognition is a broadly studied field in computer vision and suffers from the same problems noted above due to the diversity of fonts and complicated backgrounds. In this paper, we focus on the text recognition problem and mainly make three contributions toward these …
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）
Unsupervised domain adaptation addresses the problem of classifying data in an unlabeled target domain, given labeled source domain data that share a common label space but follow a different distribution. Most of the recent methods take the approach of explicitly aligning feature distributions between the two domains. Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data. Technically, we use clust…
NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；MILA, University of Montreal（蒙特利尔大学MILA）
Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations directly from raw data. Nevertheless, we believe that the long-and-well investigated domain-specific knowledge should still help to boost the performance of HCCR. By integrating the traditional normalization-cooperated direction-decomposed feature map (directMap) with the deep convolutional neural network (convNet), we are able to obtain new highest accuracies for both online and offline HCCR on the ICDAR-2013 competit…
Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption (TTA) continues to adapt the model after deployment. Recently, the area of continual and gradual test-time adaptation (TTA) emerged. In contrast to standard TTA, continual TTA considers not only a single domain shift, but a sequence of shifts. Gradual TTA further exploits the property that some shifts evolve gradually over time. Since in both settings long test sequences are present, error accumulation needs to be addressed for methods relying on self-training. In this work, we propose and show that…
Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in the autonomous driving scenario. Previous works usually tackle this issue with Unsupervised Domain Adaptation (UDA), which entails training a network on synthetic images and applying the model to real ones while minimizing the discrepancy between the two domains. Yet, these techniques do not consider additional information that may be obtained from other tasks. Differently, we propose to exploit self-supervised monocu…
UBTECH Sydney Artificial Intelligence Centre（优必选悉尼人工智能中心）；University of Sydney（悉尼大学）；University of Technology Sydney（悉尼科技大学）；Hangzhou Dianzi University（杭州电子科技大学）
Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises. However, the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit th…
Continual Model Merging with Test-Time Adaptation for Whole-Slide Image Analysis
University of Information Technology（信息技术大学）；Viet Nam National University Ho Chi Minh City（胡志明市越南国立大学）；ETIS (UMR 8051), CY Cergy Paris University, ENSEA, CNRS, France（法国赛尔齐巴黎大学、ENSEA、法国国家科学研究中心的ETIS（UMR 8051））
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification
Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiaotong University（上海交通大学）；Shanghai Ruijing Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属瑞金医院）；Shanghai Tenth People’s Hospital of Tongji University（同济大学附属上海市第十人民医院）；Xuzhou Central Hospital（徐州市中心医院）；Renji Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属仁济医院）；Sensetime Research（商汤科技研究院）；The First Affiliated Hospital of Zhengzhou University（郑州大学第一附属医院）；West China Hospital, Sichuan University（四川大学华西医院）
HyperTTA: Test-Time Adaptation for Hyperspectral Image Classification under Distribution Shifts
School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）；School of Electronic Information, Central South University（电子信息学院，中南大学）；Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University（遥感与地理信息系统研究所，地球与空间科学学院，北京大学）；School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology（遥感与地理信息工程学院，南京信息工程大学）；College of Electrical and Information Engineering, Hunan University（电气与信息工程学院，湖南大学）；Peng Cheng Laboratory（鹏城实验室）
We study the problem of robust domain adaptation in the context of unavailable target labels and source data. The considered robustness is against adversarial perturbations. This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data. The major findings of this paper are: (i) robust source models can be transferred robustly to the target; (ii) robust domain adaptation can greatly benefit from non-robust pseudo-labels and the pair-wise contrastive loss. The proposed meth…
Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation (MM-CTTA) as a new extension of CTTA for 3D semantic segmentation. The key to MM-CTTA is to adaptively attend to the reliable modality while avoiding catastrophic forgetting during continual domain shifts, which is out of the capability of previous TTA or CTTA methods. To fulfill this gap, we propose an MM-CTTA method called Continual Cross-Modal Adaptive Clu…
Robust face clustering is a vital step in enabling computational understanding of visual character portrayal in media. Face clustering for long-form content is challenging because of variations in appearance and lack of supporting large-scale labeled data. Our work in this paper focuses on two key aspects of this problem: the lack of domain-specific training or benchmark datasets, and adapting face embeddings learned on web images to long-form content, specifically movies. First, we present a dataset of over 169,000 face tracks curated from 240 Hollywood movies with weak labels on whether a pa…
University of California, Berkeley（加利福尼亚大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain. Unfortunately, direct transfer across domains often performs poorly due to the presence of domain shift or dataset bias. Domain adaptation is a machine lear…
Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well. However, existing distribution shift benchmarks with unlabeled data do not reflect the breadth of scenarios that arise in real-world applications. In this work, we present the WILDS 2.0 update, which extends 8 of the 10 datase…
The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. One method commonly employed to counter distribution shifts is domain adaptation: using samples from the target domain to learn to account for shifted distributions. In this work we propose an unsupervised domain adaptation approach that uses graph neural networks and, disentangled semantic and domain invariant structural features, allowing for better performance acr…
Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining
School of Computing, Engineering \& Mathematical Sciences, La Trobe University, Melbourne, Australia；School of Engineering；Applied Sciences, GIFT University, Gujranwala 52250, Pakistan
We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch between source and target in domain adaptation, we devise a method that addresses the issue for the first time in ADA. At its heart lies a novel sampling strategy, which seeks target data that best approximate the entire target distribution as well as being representative, diverse, and uncertain. The sampled target data are then used not only for supervised…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Machine learning techniques used in computer-aided medical image analysis usually suffer from the domain shift problem caused by different distributions between source/reference data and target data. As a promising solution, domain adaptation has attracted considerable attention in recent years. The aim of this paper is to survey the recent advances of domain adaptation methods in medical image analysis. We first present the motivation of introducing domain adaptation techniques to tackle domain heterogeneity issues for medical image analysis. Then we provide a review of recent domain adaptati…
