Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn informative representations from partial point clouds. We leverage partial point clouds scanned by LiDAR that contain both content and pose attributes, and we show that disentangling such two factors from partial point clouds enhances feature representation learning. To this end, our framework consists of three main parts: 1) a completion network to capture holistic semantics of point clouds; 2) a pose regression network to understand the viewing angle where partial data is scanned from; 3) a partial reconstruction network to encourage the model to learn content and pose features. To demonstrate the robustness of the learnt feature representations, we conduct several downstream tasks including classification, part segmentation, and registration, with comparisons against state-of-the-art methods. Our method not only outperforms existing self-supervised methods, but also shows a better generalizability across synthetic and real-world datasets.
Tel Aviv University（特拉维夫大学）；Hebrew University of Jerusalem（希伯来大学）
We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant, while the extracted rotation and translation are able to semantically align different input shapes of the same class to a common canonical pose. Specifically, we design an auto-encoder based on Vector Neuron Networks, a rotation-equivariant neural network, whose layers we extend to provide translation-equivariance in addition to rotation-equivariance only. The resu…
Carnegie Mellon University（卡内基梅隆大学）；NVIDIA（英伟达）；UC Berkeley（加州大学伯克利分校）；UC San Diego（加州大学圣地亚哥分校）
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in nearby video frames remains static. Given a sequence of video frames as input, the video autoencoder extracts a disentangled representation of the scene includ- ing: (i) a temporally-consistent deep voxel feature to represent the 3D structure and (ii) a 3D trajectory of camera pose for each frame. These two representations will then be re-entangled for render…
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
Tianjin University（天津大学）；Eastern Institute of Technology（东方理工学院）；Ningbo Institute of Digital Twin（宁波数字孪生研究院）；Shanghai Jiao Tong University（上海交通大学）；Northwest Normal University（西北师范大学）；Zhejiang University（浙江大学）
University of Toronto（多伦多大学）；Vector Institute for AI（矢量人工智能研究院）；Samsung AI Center Toronto（多伦多三星人工智能中心）；Samsung Research America, Inc.（美国三星研究公司）
Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of generative models. However, it remains an open problem to learn a generative model of shape that is interpretable and easily manipulated, particularly in the absence of supervised labels. In this paper, we propose an unsupervised approach to partitioning the latent space of a variational autoencoder for 3D point clouds in a natural way, using only geometric inform…
Content and style (C-S) disentanglement intends to decompose the underlying explanatory factors of objects into two independent subspaces. From the unsupervised disentanglement perspective, we rethink content and style and propose a formulation for unsupervised C-S disentanglement based on our assumption that different factors are of different importance and popularity for image reconstruction, which serves as a data bias. The corresponding model inductive bias is introduced by our proposed C-S disentanglement Module (C-S DisMo), which assigns different and independent roles to content and sty…
Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a self-supervised framework DisCont to disentangle multiple attributes by exploiting the structural inductive biases within images. Motivated by the recent surge in contrastive learning paradigms, our model bridges the gap between self-supervised contrastive learning algorithms and unsupervised disentanglement. We evaluate the efficacy of our approach, both qualitative…
NEC Labs America（NEC美国实验室）；Rutgers University（罗格斯大学）
We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals from input data itself or some off-the-shelf functional models and accordingly design auxiliary tasks for our model to utilize these signals. With the supervision of the signals, our model can easily disentangle the representation of an input sequence into static factors and dynamic factors (i.e., time-invariant and time-varying parts). Comprehensive experim…
National Taiwan University（台湾大学）；MOST Joint Research Center for AI Technology and All Vista Healthcare（科技部AI技术与全视医疗照护联合研究中心）；ASUS Intelligent Cloud Services（华硕智能云服务）
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not practical for real-world applications. To alleviate this limitation, researchers now targets at cross-dataset re-ID which focuses on generalizing the discriminative ability to the unlabeled target domain when given a labeled source domain dataset. To achieve this goal, our proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Tencent AI Lab（腾讯人工智能实验室）
One-shot video-driven talking face generation aims at producing a synthetic talking video by transferring the facial motion from a video to an arbitrary portrait image. Head pose and facial expression are always entangled in facial motion and transferred simultaneously. However, the entanglement sets up a barrier for these methods to be used in video portrait editing directly, where it may require to modify the expression only while maintaining the pose unchanged. One challenge of decoupling pose and expression is the lack of paired data, such as the same pose but different expressions. Only a…
Enormous hand images with reliable annotations are collected through marker-based MoCap. Unfortunately, degradations caused by markers limit their application in hand appearance reconstruction. A clear appearance recovery insight is an image-to-image translation trained with unpaired data. However, most frameworks fail because there exists structure inconsistency from a degraded hand to a bare one. The core of our approach is to first disentangle the bare hand structure from those degraded images and then wrap the appearance to this structure with a dual adversarial discrimination (DAD) scheme…
3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
The Chinese University of Hong Kong（香港中文大学）；T Stone Robotics Institute of CUHK（香港中文大学汤申机器人研究所）
Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view variations are two critical issues. In this work, we propose a novel Siamese denoising autoencoder to learn a 3D pose representation by disentangling the pose-dependent and view-dependent feature from the human skeleton data, in a fully unsupervised manner. These two disentangled features are utilized together as the representation of the 3D pose. To consider both t…
Human interpretation of the world encompasses the use of symbols to categorize sensory inputs and compose them in a hierarchical manner. One of the long-term objectives of Computer Vision and Artificial Intelligence is to endow machines with the capacity of structuring and interpreting the world as we do. Towards this goal, recent methods have successfully been able to decompose and disentangle video sequences into their composing objects and dynamics, in a self-supervised fashion. However, there has been a scarce effort in giving interpretation to the dynamics of the scene. We propose a metho…
University of Edinburgh（爱丁堡大学）；Canon Medical Research Europe Ltd.（佳能医疗欧洲研究有限公司）；The Alan Turing Institute（艾伦·图灵研究所）
Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based meta-learning approaches where the training data are split into meta-train and meta-test sets to simulate and handle the domain shifts during training have shown improved generalisation performance. However, the current fully supervised meta-learning approaches are not scalable for medical image segmentation, where large effort is required to create pixel-wise annotati…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Parametric models of humans, faces, hands and animals have been widely used for a range of tasks such as image-based reconstruction, shape correspondence estimation, and animation. Their key strength is the ability to factor surface variations into shape and pose dependent components. Learning such models requires lots of expert knowledge and hand-defined object-specific constraints, making the learning approach unscalable to novel objects. In this paper, we present a simple yet effective approach to learn disentangled shape and pose representations in an unsupervised setting. We use a combina…
Rice University（莱斯大学）；Nvidia（英伟达）；University of Toronto（多伦多大学）；California Institute of Technology（加州理工学院）
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We i…
DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
School of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学人工智能与先进计算学院）；Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电子与计算机工程系）；Computer Vision Institute, School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院计算机视觉研究所）；Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University（广东省智能信息处理重点实验室，深圳大学）
Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is to factorize an image into a pose and appearance data stream, then to reconstruct the image from the factorized components. The pose representation should capture a set of consistent and tightly localized landmarks in order to facilitate reconstruction of the input image. Ultimately, we wish for our learned landmarks to focus on the foreground object of interest. However, the reconstruction task of the entire image fo…
NEC Laboratories America（NEC美国实验室）；Rutgers, The State University of New Jersey（罗格斯大学新泽西州立大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
Deep neural networks (DNNs) trained on large-scale datasets have recently achieved impressive improvements in face recognition. But a persistent challenge remains to develop methods capable of handling large pose variations that are relatively underrepresented in training data. This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive pose coverage in training data. We first propose to generate non-frontal views from a single frontal face, in order to increase the diversity of training data while preserving accurate facial details…
Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification
Shanghai Jiao Tong University School of Medicine（上海交通大学医学院）；Ruijin Hospital（瑞金医院）；Fudan University（复旦大学）；Shandong Provincial Hospital Affiliated to Shandong First Medical University（山东第一医科大学附属省立医院）；Air Force Medical University（空军军医大学）
EASL: Multi-Emotion Guided Semantic Disentanglement for Expressive Sign Language Generation
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）；University of Health and Rehabilitation Sciences（康复科学大学）；The University of Aberdeen（阿伯丁大学）
While recent person re-identification (ReID) methods achieve high accuracy in a supervised setting, their generalization to an unlabelled domain is still an open problem. In this paper, we introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue of supervised person ReID. Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain. …
Xi’an Jiaotong University（西安交通大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua University（清华大学）
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i.e.style feature, and the feature representing the invariant semantic content, i.e. content feature. Previous methods separate content feature apart by utilizing it to classify haze image during the training process. However, in this paper we recognize the incompleteness of the content-style disentanglement in such technical routine. The flawed style feature entangled with content information inevitably leads the ill-rendering of the haze im…
We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both locations and semantics, they are an attractive target for supervised learning approaches. However, large annotation costs limit the scalability of supervised algorithms to other object categories than humans. Unsupervised approaches potentially allow to use much more data at a lower cost. Most existing unsupervised approaches focus on learning abstract rep…
University of Rochester（罗切斯特大学）；University of Maryland, College Park（马里兰大学帕克分校）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods which rely heavily on synthesized data for training. However, as synthesized data may not perfectly simulate the underlying physical mechanisms of CT imaging, the supervised methods often generalize poorly to clinical applications. To address this problem, we propose, to the best of our knowledge, the first unsupervised learning approach to MAR. Specifically, we introduce a novel artifact disentanglement network that enables different forms of generations and regulariz…
Geometric disentanglement, the separation of latent codes for intrinsic (i.e. identity) and extrinsic(i.e. pose) geometry, is a prominent task for generative models of non-Euclidean data such as 3D deformable models. It provides greater interpretability of the latent space, and leads to more control in generation. This work introduces a mesh feature, the conformal factor and normal feature (CFAN),for use in mesh convolutional autoencoders. We further propose CFAN-VAE, a novel architecture that disentangles identity and pose using the CFAN feature. Requiring no label information on the identity…
Tsinghua University（清华大学）；UC San Diego（加州大学圣地亚哥分校）；Qualcomm, Inc.（高通公司）；University of Amsterdam（阿姆斯特丹大学）
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning. The learning objective is achieved by providing signals to the latent encoding/embedding in VAE without changing its main backbone architecture, hence retaining the desirable properties of the VAE. We design an unsupervised strategy and a supervised strategy in Guided-VAE and observe enhanced modeling and controlling capability over the vanilla VAE. In the unsupervised strategy, we guide the VAE learning by int…
TCS Research（塔塔咨询服务研究部）；Flytxt Mobile Solutions（Flytxt 移动解决方案公司）；Indian Institute of Space Science and Technology（印度空间科学技术研究所）
Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised methods since they do not use pre-trained attribute classifiers. We propose Scale Ranking Estimator (SRE), which is trained using self-supervision. SRE enhances the disentanglement in directions obtained by existing unsupervised disentanglement techniques. These directions are updated to preserve the ordering of variation within each direction in latent space. Qualitative and qua…
Image search engines enable the retrieval of images relevant to a query image. In this work, we consider the setting where a query for similar images is derived from a collection of images. For visual search, the similarity measurements may be made along multiple axes, or views, such as style and color. We assume access to a set of feature extractors, each of which computes representations for a specific view. Our objective is to design a retrieval algorithm that effectively combines similarities computed over representations from multiple views. To this end, we propose a self-supervised learn…
University of Rochester（罗切斯特大学）；University of Maryland, College Park（马里兰大学帕克分校）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Peng Cheng Laboratory（鹏城实验室）
Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training. However, as synthesized data may not accurately simulate the underlying physical mechanisms of CT imaging, the supervised methods often generalize poorly to clinical applications. To address this problem, we propose, to the best of our knowledge, the first unsupervised learning approach to MAR. Specifically, we introduce a novel artifact disentanglement network that disentangles the metal artifacts from CT images i…
Australian National University（澳大利亚国立大学）；Tsinghua University（清华大学）；ShanghaiTech University（上海科技大学）
There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either using training images with annotations or regulating the training process with external clues such as human skeleton, body segmentation or cloth patches etc. In this paper, we aim to address this challenge in a more unsupervised manner---we do not require any annotation nor any external task-specific clues. To this end, we formulate an encoder-decoder-like network to extract both the shape and appearance features from in…
We propose a way of learning disentangled content-style representation of image, allowing us to extrapolate images to any style as well as interpolate between any pair of styles. By augmenting data set in a supervised setting and imposing triplet loss, we ensure the separation of information encoded by content and style representation. We also make use of cycle-consistency loss to guarantee that images could be reconstructed faithfully by their representation.
Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）；Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）；Department of Biomedical Engineering, University of Utah（犹他大学生物医学工程系）；Nora Eccles Harrison Cardiovascular Research and Training Institute, University of Utah（犹他大学诺拉·埃克尔斯·哈里森心血管研究与培训研究所）；Department of Radiology and Imaging Sciences, University of Utah（犹他大学放射学与影像科学系）；Department of Biomedical Engineering, Johns Hopkins（约翰霍普金斯大学生物医学工程系）；Division of Cardiology, University of Utah（犹他大学心脏病学系）
Institute of Neuroinformatics, ETH Zurich（苏黎世联邦理工学院神经信息学研究所）
Disentanglement is at the forefront of unsupervised learning, as disentangled representations of data improve generalization, interpretability, and performance in downstream tasks. Current unsupervised approaches remain inapplicable for real-world datasets since they are highly variable in their performance and fail to reach levels of disentanglement of (semi-)supervised approaches. We introduce population-based training (PBT) for improving consistency in training variational autoencoders (VAEs) and demonstrate the validity of this approach in a supervised setting (PBT-VAE). We then use Unsupe…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术研究所）
Video Prediction is an interesting and challenging task of predicting future frames from a given set context frames that belong to a video sequence. Video prediction models have found prospective applications in Maneuver Planning, Health care, Autonomous Navigation and Simulation. One of the major challenges in future frame generation is due to the high dimensional nature of visual data. In this work, we propose Mutual Information Predictive Auto-Encoder (MIPAE) framework, that reduces the task of predicting high dimensional video frames by factorising video representations into content and lo…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features in a target domain is an interesting and difficult problem that is rarely discussed in the current literature. This problem is essential for many real-world applications such as improving diagnostic classification or prediction in medical imaging. To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract ge…
Learning disentangled representations is regarded as a fundamental task for improving the generalization, robustness, and interpretability of generative models. However, measuring disentanglement has been challenging and inconsistent, often dependent on an ad-hoc external model or specific to a certain dataset. To address this, we present a method for quantifying disentanglement that only uses the generative model, by measuring the topological similarity of conditional submanifolds in the learned representation. This method showcases both unsupervised and supervised variants. To illustrate the…
