Fine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Training a model in one environment and deploying in another results in a drop in performance due to an unavoidable domain shift. Unsupervised Domain Adaptation (UDA) approaches have frequently utilised adversarial training between the source and target domains. However, these approaches have not explored the multi-modal nature of video within each domain. In this work we exploit the correspondence of modalities as a self-supervised alignment approach for UDA in addition to adversarial alignment.
We test our approach on three kitchens from our large-scale dataset, EPIC-Kitchens, using two modalities commonly employed for action recognition: RGB and Optical Flow. We show that multi-modal self-supervision alone improves the performance over source-only training by 2.4% on average. We then combine adversarial training with multi-modal self-supervision, showing that our approach outperforms other UDA methods by 3%.
While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in every new scenario, a task that is infeasible. However, sources such as e-commerce websites and field guides provide annotated images for many classes. In this work, we study fine-grained domain adaptation as a step towards overcoming the dataset shift between easily acquired annotated images and the real world. Adaptation has not been studied in the fine-gr…
Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation, we propose cross-modal learning, where we enforce consistency between the predictions of two modalities via mutual mimicking. We constrain our network to make correct predictions on labeled data and consistent predictions across modalities on unlabeled target-domain data. Experiments in unsupervised and semi-supervised domain adaptation settings prove the eff…
Sichuan University（四川大学）；University of Electronic Science and Technology of China（电子科技大学）；Dalian University of Technology（大连理工大学）；National University of Defense Technology（国防科技大学）
Domain adaptation is critical for success when confronting with the lack of annotations in a new domain. As the huge time consumption of labeling process on 3D point cloud, domain adaptation for 3D semantic segmentation is of great expectation. With the rise of multi-modal datasets, large amount of 2D images are accessible besides 3D point clouds. In light of this, we propose to further leverage 2D data for 3D domain adaptation by intra and inter domain cross modal learning. As for intra-domain cross modal learning, most existing works sample the dense 2D pixel-wise features into the same size…
Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学）；German Aerospace Center (DLR)（德国航空航天中心）
Deep-learning methods offer unsurpassed recognition performance in a wide range of domains, including fine-grained recognition tasks. However, in most problem areas there are insufficient annotated training samples. Therefore, the topic of transfer learning respectively domain adaptation is particularly important. In this work, we investigate to what extent unsupervised domain adaptation can be used for fine-grained recognition in a biodiversity context to learn a real-world classifier based on idealized training data, e.g. preserved butterflies and plants. Moreover, we investigate the influen…
Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation
College of Computer and Cyber Security, Fujian Normal University（计算机与网络安全部，福建师范大学）；Department of Computer Science, National Tsing Hua University（计算机科学系，国立清华大学）
Boston University（波士顿大学）；NEC Labs America（NEC美国实验室）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data is usually associated with multi-modal information, e.g., RGB and optical flow, and thus it remains a challenge to design a better method that considers the cross-modal inputs under the cross-domain adaptation setting. To this end, we propose a unified framework for video domain adaptation, which si…
Due to the large cross-modality discrepancy between 2D sketches and 3D shapes, retrieving 3D shapes by sketches is a significantly challenging task. To address this problem, we propose a novel framework to learn a discriminative deep cross-modality adaptation model in this paper. Specifically, we first separately adopt two metric networks, following two deep convolutional neural networks (CNNs), to learn modality-specific discriminative features based on an importance-aware metric learning method. Subsequently, we explicitly introduce a cross-modality transformation network to compensate for t…
Radboud University Medical Center（拉德堡德大学医学中心）；The Netherlands Cancer Institute（荷兰癌症研究所）；Nanjing University of Information Science and Technology（南京信息工程大学）
Domain adaptation has been widely adopted to transfer styles across multi-vendors and multi-centers, as well as to complement the missing modalities. In this challenge, we proposed an unsupervised domain adaptation framework for cross-modality vestibular schwannoma (VS) and cochlea segmentation and Koos grade prediction. We learn the shared representation from both ceT1 and hrT2 images and recover another modality from the latent representation, and we also utilize proxy tasks of VS segmentation and brain parcellation to restrict the consistency of image structures in domain adaptation. After …
Northwestern University（西北大学）；Futurewei Technologies（华为未来技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；University of Rochester（罗切斯特大学）
We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and ans…
Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of annotations in a new domain. There are many multi-modal datasets, but most UDA approaches are uni-modal. In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation. This is challenging as the two input spaces are heterogeneous and can be impacted differently by domain shift. In xMUDA, modalities learn from each other through mutual mimicking, disentangled from the segmentation objective, to prevent th…
MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On
Harbin Institute of Technology（哈尔滨工业大学）；HiDream.ai Inc.（HiDream.ai公司）；Harbin Institute of Technology (Weihai) Qingdao Research Institute（哈尔滨工业大学（威海）青岛研究院）
Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学系）；Department of Computing, Imperial College London（帝国理工学院计算机系）；Department of Electrical Engineering and Computer Science, University of Michigan（密歇根大学电气工程与计算机科学系）；Imsight Medical Technology, Co, Ltd., China（中国医视医疗科技有限公司）；School of Data Science, Fudan University, China（复旦大学数据科学学院）
Deep convolutional networks have demonstrated the state-of-the-art performance on various medical image computing tasks. Leveraging images from different modalities for the same analysis task holds clinical benefits. However, the generalization capability of deep models on test data with different distributions remain as a major challenge. In this paper, we propose the PnPAdaNet (plug-and-play adversarial domain adaptation network) for adapting segmentation networks between different modalities of medical images, e.g., MRI and CT. We propose to tackle the significant domain shift by aligning t…
The Chinese University of Hong Kong（香港中文大学）；University of Leicester（莱斯特大学）
Domain adaptation is crucial for transferring the knowledge from the source labeled CT dataset to the target unlabeled MR dataset in abdominal multi-organ segmentation. Meanwhile, it is highly desirable to avoid the high annotation cost related to the target dataset and protect the source dataset privacy. Therefore, we propose an effective source-free unsupervised domain adaptation method for cross-modality abdominal multi-organ segmentation without source dataset access. The proposed framework comprises two stages. In the first stage, the feature map statistics-guided model adaptation combine…
Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image Segmentation
School of Computer Technology and Applications, Qinghai University（青海大学计算机技术与应用学院）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention（上海市医学影像计算与计算机辅助干预重点实验室）
Unsupervised domain adaptation (UDA) aims to learn a model trained on source domain and performs well on unlabeled target domain. In medical image segmentation field, most existing UDA methods depend on adversarial learning to address the domain gap between different image modalities, which is ineffective due to its complicated training process. In this paper, we propose a simple yet effective UDA method based on frequency and spatial domain transfer uner multi-teacher distillation framework. In the frequency domain, we first introduce non-subsampled contourlet transform for identifying domain…
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；SenseTime Research（商汤科技研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
As one of the fundamental functions of autonomous driving system, freespace detection aims at classifying each pixel of the image captured by the camera as drivable or non-drivable. Current works of freespace detection heavily rely on large amount of densely labeled training data for accuracy and robustness, which is time-consuming and laborious to collect and annotate. To the best of our knowledge, we are the first work to explore unsupervised domain adaptation for freespace detection to alleviate the data limitation problem with synthetic data. We develop a cross-modality domain adaptation f…
University of Bristol（布里斯托大学）；NAVER LABS Europe（NAVER LABS 欧洲）
Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query. To compensate for the lack of annotations, we rely instead on a related video gallery composed of video-caption pairs, termed the source gallery, albeit with a domain gap between its videos and those in the target gallery. We thus introduce the problem of Unsupervised Domain Adaptation for Cross-modal Video Retrieval, along with a new benchmark on fine-grained actions. We propose a novel iterative domain alignment method by means of pseudo-labelli…
Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；PengCheng Laboratory（鹏城实验室）
TU Wien（维也纳工业大学）；Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions. In robotics, DA is used to take advantage of automatically generated synthetic data, that come with "free" annotation, to make effective predictions on real data. However, existing DA methods are not designed to cope with the multi-modal nature of RGB-D data, which are widely used in robotic vision. We propose a novel RGB-D DA method that reduces the synthetic-to-real domain shift by exploiting the inter-modal rel…
Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for cross-modality medical data with a notable domain shift. Given that specific annotated imaging modalities may not be accessible nor complete. Our proposed solution is based on the cross-modality synthesis of medical images to reduce the costly annotation burden by radiologists and bridge the domain gap in radiological images. We present a novel approach for …
Cornell University（康奈尔大学）；Google（谷歌）；University of Edinburgh（爱丁堡大学）；University of Copenhagen（哥本哈根大学）
We present a new benchmark dataset, Sapsucker Woods 60 (SSW60), for advancing research on audiovisual fine-grained categorization. While our community has made great strides in fine-grained visual categorization on images, the counterparts in audio and video fine-grained categorization are relatively unexplored. To encourage advancements in this space, we have carefully constructed the SSW60 dataset to enable researchers to experiment with classifying the same set of categories in three different modalities: images, audio, and video. The dataset covers 60 species of birds and is comprised of i…
Department of Biomedical Engineering, Yale University（耶鲁大学生物医学工程系）；Department of Radiology & Biomedical Imaging, Yale School of Medicine（耶鲁大学医学院放射科与生物医学成像系）；Department of Electrical Engineering, Yale University（耶鲁大学电气工程系）；Department of Statistics & Data Science, Yale University（耶鲁大学统计与数据科学系）；Yale School of Medicine（耶鲁大学医学院）；Yale University（耶鲁大学）
A deep learning model trained on some labeled data from a certain source domain generally performs poorly on data from different target domains due to domain shifts. Unsupervised domain adaptation methods address this problem by alleviating the domain shift between the labeled source data and the unlabeled target data. In this work, we achieve cross-modality domain adaptation, i.e. between CT and MRI images, via disentangled representations. Compared to learning a one-to-one mapping as the state-of-art CycleGAN, our model recovers a many-to-many mapping between domains to capture the complex c…
The Koos grading scale is a classification system for vestibular schwannoma (VS) used to characterize the tumor and its effects on adjacent brain structures. The Koos classification captures many of the characteristics of treatment deci-sions and is often used to determine treatment plans. Although both contrast-enhanced T1 (ceT1) scanning and high-resolution T2 (hrT2) scanning can be used for Koos Classification, hrT2 scanning is gaining interest because of its higher safety and cost-effectiveness. However, in the absence of annotations for hrT2 scans, deep learning methods often inevitably s…
Nanjing University of Science and Technology（南京理工大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
TIReID aims to retrieve the image corresponding to the given text query from a pool of candidate images. Existing methods employ prior knowledge from single-modality pre-training to facilitate learning, but lack multi-modal correspondences. Besides, due to the substantial gap between modalities, existing methods embed the original modal features into the same latent space for cross-modal alignment. However, feature embedding may lead to intra-modal information distortion. Recently, CLIP has attracted extensive attention from researchers due to its powerful semantic concept learning capacity an…
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation. We find that directly applying existing methods usually results in performance instability at test time because multi-modal input is not considered jointly. To design a framework that can take full advantage of multi-modality, where each modality provides regularized self-supervisory signals to other modalities, we propose two compl…
Institute of Industrial Science, the University of Tokyo（东京大学生产技术研究所）
In this report, we describe the technical details of our submission to the 2021 EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition. Leveraging multiple modalities has been proved to benefit the Unsupervised Domain Adaptation (UDA) task. In this work, we present Multi-Modal Mutual Enhancement Module (M3EM), a deep module for jointly considering information from multiple modalities to find the most transferable representations across domains. We achieve this by implementing two sub-modules for enhancing each modality using the context of other modalities. The first…
Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension
School of Software Technology, Zhejiang University（浙江大学软件学院）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Zhejiang University-University of Illinois at Urbana-Champaign Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校研究院）
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机技术研究所）
With the prevalence of RGB-D cameras, multi-modal video data have become more available for human action recognition. One main challenge for this task lies in how to effectively leverage their complementary information. In this work, we propose a Modality Compensation Network (MCN) to explore the relationships of different modalities, and boost the representations for human action recognition. We regard RGB/optical flow videos as source modalities, skeletons as auxiliary modality. Our goal is to extract more discriminative features from source modalities, with the help of auxiliary modality. B…
CoMLP: Cooperatively-Gated MLPs for Fine-Grained Cross-Modal Information Fusion in Medical Image Segmentation
Institute of Translational Medicine, Shanghai Jiao Tong University（上海交通大学转化医学研究院）；Zhongguancun Academy（中关村学院）；Zhongguancun Institute of Artificial Intelligence（中关村人工智能研究院）；School of Computer Science, the University of Sydney（悉尼大学计算机学院）；China United Network Communications Group Co., Ltd.（中国联合网络通信集团有限公司）
Boston University（波士顿大学）；Kuaishou Technology（快手科技）
Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the text with fine-grained features which relies on complicated model designs, or modeling fine-grained interaction via cross-attention upon visual and textual tokens which suffers from inferior efficiency. To address these limitations, some recent works simply aggregate the token-wise similarities to achieve fine-grained alignment, but they lack intuitive expla…
Fine-Grained Scene Image Classification with Modality-Agnostic Adapter
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Innovation Center of Calligraphy and Painting Creation Technology, MCT（中国传媒书画创作技术创新中心）；Videt Technology（维德科技）
Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of visual and textual cues to tackle the task of fine-grained image classification and retrieval. First, we obtain the text instances from images by employing a text reading system. Then, we combine textual features with salient image regions to exploit the complementary information carried by the two sources. Specifically, we employ a Graph Convolutional Network …
UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse Annotations
