There are many forms of feature information present in video data. Principle among them are object identity information which is largely static across multiple video frames, and object pose and style information which continuously transforms from frame to frame. Most existing models confound these two types of representation by mapping them to a shared feature space. In this paper we propose a probabilistic approach for learning separable representations of object identity and pose information using unsupervised video data. Our approach leverages a deep generative model with a factored prior distribution that encodes properties of temporal invariances in the hidden feature set. Learning is achieved via variational inference. We present results of learning identity and pose information on a dataset of moving characters as well as a dataset of rotating 3D objects. Our experimental results demonstrate our model's success in factoring its representation, and demonstrate that the model achieves improved performance in transfer learning tasks.
Imperial College London（帝国理工学院）；UC Berkeley（加州大学伯克利分校）
Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks together in order to capture task relationships, at an extremely high computational cost. In this work, we learn task relationships via an automated weighting framework, named Auto-Lambda. Unlike previous methods where task relationships are assumed to be fixed, Auto-Lambda is a gradient-based meta learning framework which explores continuous, dynamic task relationships via task…
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating factors are also statistically independent, disentangled representations can be formed by Bayesian inference of latent variables. We examine a generalization of the Variational Autoencoder (VAE), $β$-VAE, for learning such representations using variational inference. $β$-VAE enforces conditional independence of its bottleneck neurons controlled by its hyperparameter $β$. This condition is in general not compatible wit…
Computer Science and Artificial Intelligence Laboratory（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
Multimodal sensory data resembles the form of information perceived by humans for learning, and are easy to obtain in large quantities. Compared to unimodal data, synchronization of concepts between modalities in such data provides supervision for disentangling the underlying explanatory factors of each modality. Previous work leveraging multimodal data has mainly focused on retaining only the modality-invariant factors while discarding the rest. In this paper, we present a partitioned variational autoencoder (PVAE) and several training objectives to learn disentangled representations, which e…
Rank-Order N-of-M Codes for Sparse Distributed Memory: Disentangling Representation and Learning Effects in Noise Robustness Against Contemporary Neuromorphic Architectures
What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density. We show that the auto-encoder captures the score (derivative of the log-density with respect to the input). It contradicts previous interpretations of reconstructi…
Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently generate new data necessary for a particular task. Learning disentangled representations is a challenging problem, especially when certain factors of variation are difficult to label. In this paper, we introduce a novel architecture that disentangles the latent space into two complementary subspaces by using only weak supervision in form of pairwise similarity…
Beijing University of Posts and Telecommunications（北京邮电大学）
Facial expression recognition (FER) is a challenging problem because the expression component is always entangled with other irrelevant factors, such as identity and head pose. In this work, we propose an identity and pose disentangled facial expression recognition (IPD-FER) model to learn more discriminative feature representation. We regard the holistic facial representation as the combination of identity, pose and expression. These three components are encoded with different encoders. For identity encoder, a well pre-trained face recognition model is utilized and fixed during training, whic…
VAE requires the standard Gaussian distribution as a prior in the latent space. Since all codes tend to follow the same prior, it often suffers the so-called "posterior collapse". To avoid this, this paper introduces the class specific distribution for the latent code. But different from CVAE, we present a method for disentangling the latent space into the label relevant and irrelevant dimensions, $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$, for a single input. We apply two separated encoders to map the input into $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$ respectively, and then give the conc…
In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and closely related structures have remained popular because they are easy to train and adapt to different tasks. An interesting question is if we can achieve state-of-the-art performance with AEs while retaining their good properties. We propose an answer to this question by introducing a new model called Y-Autoencoder (Y-AE). The structure and training procedure…
Deep feature spaces have the capacity to encode complex transformations of their input data. However, understanding the relative feature-space relationship between two transformed encoded images is difficult. For instance, what is the relative feature space relationship between two rotated images? What is decoded when we interpolate in feature space? Ideally, we want to disentangle confounding factors, such as pose, appearance, and illumination, from object identity. Disentangling these is difficult because they interact in very nonlinear ways. We propose a simple method to construct a deep fe…
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Conservatoire National des Arts et Métiers（法国国立工艺学院）
In computer vision, disentangling techniques aim at improving latent representations of images by modeling factors of variation. In this paper, we propose DualDis, a new auto-encoder-based framework that disentangles and linearizes class and attribute information. This is achieved thanks to a two-branch architecture forcing the separation of the two kinds of information, accompanied by a decoder for image reconstruction and generation. To effectively separate the information, we propose to use a combination of regular and adversarial classifiers to guide the two branches in specializing for cl…
The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the choice of dataset-specific hyperparameters, in particular the regularization strength. To address this issue, we introduce DAVA, a novel training procedure for variational auto-encoders. DAVA completely alleviates the problem of hyperparameter selection. We compare DAVA to models with optimal hyperparameters. Without any hyperparameter tuning, DAVA is compe…
Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair representation learning. This network disentangles latent space into three subspaces with a decorrelation loss that encourages each subspace to contain independent information: 1) target attribute information, 2) protected attribute information, 3) mutual attribute information. After the representation learning, this disentangled representation is leveraged for fairer …
University of Bonn（波恩大学）；National University of Singapore（新加坡国立大学）
Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint. To better analyze these factors of variation, we propose the use of disentangled representations and a disentangled variational autoencoder (dVAE) that allows for specific sampling and inference of these factors. The derived objective from the variational lower bound as well as the proposed training strategy are highly flexible, allowing us to handle cross-modal encoders and decoders as we…
UC Berkeley（加州大学伯克利分校）；Sinovation Ventures AI Institute（创新工场人工智能研究院）；Columbia University（哥伦比亚大学）
A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated. Prior approaches to video prediction typically learn either to warp or to hallucinate future pixels, but not both. In this paper, we describe a computational model for high-fidelity video prediction which disentangles motion-specific propagation from motion-agnostic generation. We introduce a confidence-aware warping operator which gates the output of pixel predictions from a flow predictor for non-occluded regions a…
Shandong Provincial Key Laboratory of Network Based Intelligent Computing（山东省网络智能计算重点实验室）；University of Jinan（济南大学）；Jinan, 250022, China（济南市，250022，中国）
Disentanglement is a highly desirable property of representation due to its similarity with human's understanding and reasoning. This improves interpretability, enables the performance of down-stream tasks, and enables controllable generative models. However, this domain is challenged by the abstract notion and incomplete theories to support unsupervised disentanglement learning. We demonstrate the data itself, such as the orientation of images, plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with the action se…
This letter presents a novel framework termed DistSTN for the task of synthetic aperture radar (SAR) automatic target recognition (ATR). In contrast to the conventional SAR ATR algorithms, DistSTN considers a more challenging practical scenario for non-cooperative targets whose aspect angles for training are incomplete and limited in a partial range while those of testing samples are unlimited. To address this issue, instead of learning the pose invariant features, DistSTN newly involves an elaborated feature disentangling model to separate the learned pose factors of a SAR target from the ide…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers exciting opportunities to develop new data-driven design processes in creative disciplines, in particular, to automate the generation of multiple novel designs that are aesthetically reminiscent of the input data but that were unseen during training. However, the learned latent space is typically disorganized and entangled: traversing the latent space along a sin…
University of California, Merced（加州大学默塞德分校）；Adobe Research（奥多比研究院）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
An important problem for both graphics and vision is to synthesize novel views of a 3D object from a single image. This is particularly challenging due to the partial observability inherent in projecting a 3D object onto the image space, and the ill-posedness of inferring object shape and pose. However, we can train a neural network to address the problem if we restrict our attention to specific object categories (in our case faces and chairs) for which we can gather ample training data. In this paper, we propose a novel recurrent convolutional encoder-decoder network that is trained end-to-en…
IIIT Delhi（德里印度理工学院）；Bioinformatics Institute, A*STAR（A*STAR生物信息研究所）；Singapore University of Technology and Design（新加坡科技设计大学）
We introduce MGP-VAE (Multi-disentangled-features Gaussian Processes Variational AutoEncoder), a variational autoencoder which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled representations in video sequences. We improve upon previous work by establishing a framework by which multiple features, static or dynamic, can be disentangled. Specifically we use fractional Brownian motions (fBM) and Brownian bridges (BB) to enforce an inter-frame correlation structure in each independent channel, and show that varying this structure enables one to c…
In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. Unlike the existing domain adaptation methods that learn associated features sharing a domain, DRANet preserves the distinctiveness of each domain's characteristics. Our model encodes individual representations of content (scene structure) and style (artistic appearance) from both source and target images. Then, it adapts the domain by incorporating the transferred style factor into the content factor al…
3D face modeling has been an active area of research in computer vision and computer graphics, fueling applications ranging from facial expression transfer in virtual avatars to synthetic data generation. Existing 3D deep learning generative models (e.g., VAE, GANs) allow generating compact face representations (both shape and texture) that can model non-linearities in the shape and appearance space (e.g., scatter effects, specularities, etc.). However, they lack the capability to control the generation of subtle expressions. This paper proposes a new 3D face generative model that can decouple…
Zongmu Technology（纵目科技）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
The 3D visual perception for vehicles with the surround-view fisheye camera system is a critical and challenging task for low-cost urban autonomous driving. While existing monocular 3D object detection methods perform not well enough on the fisheye images for mass production, partly due to the lack of 3D datasets of such images. In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identific…
Sichuan University（四川大学）；Michigan State University（密歇根州立大学）
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously. Unlike existing 3D face reconstruction methods, our proposed method directly regresses dense 3D face shapes from single 2D images, and tackles identity and residual (i.e., non-identity) components in 3D face shapes explicitly and separately based on a composite 3D face shape model with latent representation…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Imperial College London（伦敦帝国理工学院）；University of Oxford（牛津大学）；Technical University of Munich（慕尼黑工业大学）
For visual manipulation tasks, we aim to represent image content with semantically meaningful features. However, learning implicit representations from images often lacks interpretability, especially when attributes are intertwined. We focus on the challenging task of extracting disentangled 3D attributes only from 2D image data. Specifically, we focus on human appearance and learn implicit pose, shape and garment representations of dressed humans from RGB images. Our method learns an embedding with disentangled latent representations of these three image properties and enables meaningful re-a…
Institute of Computing Technology, CAS（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）；University of Oulu（奥卢大学）；Peng Cheng Laboratory（鹏城实验室）
Remote physiological measurements, e.g., remote photoplethysmography (rPPG) based heart rate (HR), heart rate variability (HRV) and respiration frequency (RF) measuring, are playing more and more important roles under the application scenarios where contact measurement is inconvenient or impossible. Since the amplitude of the physiological signals is very small, they can be easily affected by head movements, lighting conditions, and sensor diversities. To address these challenges, we propose a cross-verified feature disentangling strategy to disentangle the physiological features with non-phys…
Context Disentangling and Prototype Inheriting for Robust Visual Grounding
Nanjing University of Science and Technology（南京理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；SenseTime Research（商汤科技研究院）
Recent works have shown how realistic talking face images can be obtained under the supervision of geometry guidance, e.g., facial landmark or boundary. To alleviate the demand for manual annotations, in this paper, we propose a novel self-supervised hybrid model (DAE-GAN) that learns how to reenact face naturally given large amounts of unlabeled videos. Our approach combines two deforming autoencoders with the latest advances in the conditional generation. On the one hand, we adopt the deforming autoencoder to disentangle identity and pose representations. A strong prior in talking face video…
Sun Yat-Sen University（中山大学）；National University of Singapore（新加坡国立大学）
As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been developed, but most of them perform unsatisfactorily on the data with complex structures. Recently, Adversarial Auto-Encoder (AAE) shows effectiveness on tackling such data by combining Auto-Encoder (AE) and adversarial training, but it cannot effectively extract classification information from the unlabeled data. In this work, we propose Dual Adversarial Auto-encoder (Dual-AAE) which simultaneously maximizes the li…
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…
Duke University（杜克大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
We present a self-supervised method to disentangle factors of variation in high-dimensional data that does not rely on prior knowledge of the underlying variation profile (e.g., no assumptions on the number or distribution of the individual latent variables to be extracted). In this method which we call NashAE, high-dimensional feature disentanglement is accomplished in the low-dimensional latent space of a standard autoencoder (AE) by promoting the discrepancy between each encoding element and information of the element recovered from all other encoding elements. Disentanglement is promoted e…
Beihang University（北京航空航天大学）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）；Microsoft（微软）
This paper introduces an unsupervised framework to extract semantically rich features for video representation. Inspired by how the human visual system groups objects based on motion cues, we propose a deep convolutional neural network that disentangles motion, foreground and background information. The proposed architecture consists of a 3D convolutional feature encoder for blocks of 16 frames, which is trained for reconstruction tasks over the first and last frames of the sequence. A preliminary supervised experiment was conducted to verify the feasibility of proposed method by training the …
Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University of Science and Technology（南京理工大学）；Wuyi University（五邑大学）；Singapore Management University（新加坡管理大学）
Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）；Zhengzhou University（郑州大学）
The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling (MD), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning…
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare for one to have access to a large number of data to help separate the influences. In this paper, we present a novel framework to learn this disentangled representation in a completely unsupervised manner. We address this problem in a two-branch Autoencoder framework. For the structural content branch, we project the latent factor into a soft structured point tensor and constrain it with losses derived from prior kno…
The development of a deep (stacked) convolutional auto-encoder in the Caffe deep learning framework is presented in this paper. We describe simple principles which we used to create this model in Caffe. The proposed model of convolutional auto-encoder does not have pooling/unpooling layers yet. The results of our experimental research show comparable accuracy of dimensionality reduction in comparison with a classic auto-encoder on the example of MNIST dataset.
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Xi’an Jiaotong University（西安交通大学）；Peking University（北京大学）；Carnegie Mellon University（卡内基梅隆大学）
Cryo-electron tomography (Cryo-ET) is a 3D imaging technique that enables the systemic study of shape, abundance, and distribution of macromolecular structures in single cells in near-atomic resolution. However, the systematic and efficient $\textit{de novo}$ recognition and recovery of macromolecular structures captured by Cryo-ET are very challenging due to the structural complexity and imaging limits. Even macromolecules with identical structures have various appearances due to different orientations and imaging limits, such as noise and the missing wedge effect. Explicitly disentangling th…
Université Paris Dauphine - PSL Research University（巴黎第九大学-巴黎文理研究大学）；CEREMADE（CEREMADE（巴黎第九大学应用数学研究中心））
The quality of generative models (such as Generative adversarial networks and Variational Auto-Encoders) depends heavily on the choice of a good probability distance. However some popular metrics like the Wasserstein or the Sliced Wasserstein distances, the Jensen-Shannon divergence, the Kullback-Leibler divergence, lack convenient properties such as (geodesic) convexity, fast evaluation and so on. To address these shortcomings, we introduce a class of distances that have built-in convexity. We investigate the relationship with some known paradigms (sliced distances - a synonym for Radon dista…
This paper presents the development of several models of a deep convolutional auto-encoder in the Caffe deep learning framework and their experimental evaluation on the example of MNIST dataset. We have created five models of a convolutional auto-encoder which differ architecturally by the presence or absence of pooling and unpooling layers in the auto-encoder's encoder and decoder parts. Our results show that the developed models provide very good results in dimensionality reduction and unsupervised clustering tasks, and small classification errors when we used the learned internal code as an…
Zhejiang University of Technology（浙江工业大学）；Tianjin University of Technology（天津理工大学）
Novelty detection is a important research area which mainly solves the classification problem of inliers which usually consists of normal samples and outliers composed of abnormal samples. Auto-encoder is often used for novelty detection. However, the generalization ability of the auto-encoder may cause the undesirable reconstruction of abnormal elements and reduce the identification ability of the model. To solve the problem, we focus on the perspective of better reconstructing the normal samples as well as retaining the unique information of normal samples to improve the performance of auto-…
Rutgers University（罗格斯大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Intellifusion（智融）
We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model. Our proposed model predicts 2D facial point heat maps regularized by both detection and regression loss, while uniquely exploiting recurrent learning at both spatial and temporal dimensions. At the spatial level, we add a feedback loop connection between the combined output response map and the input, in order to enable iterative coarse-to-fine face alignment using a single network model, instead of relying on traditional cascaded model ensembles. At the temporal level, we first…
Clemson University（克莱姆森大学）；City University of New York（纽约市立大学）
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dynamic-object-focused methods only partially solved the mismatch problem at the training loss level. In this paper, we accordingly propose a novel multi-frame monocular depth prediction method to solve these problems at both the prediction and supervision loss levels. Our method, called DynamicDepth, is a new framework trained via a self-supervised cy…
Suzhou University of Science and Technology（苏州科技大学）；Tianjin University（天津大学）；Suzhou Institute of Trade & Commerce（苏州经贸职业技术学院）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）
Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss (TL) is popularly used to generate realistic visual distributions from semantics by automatically searching discriminative representations. However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL. To alleviate this drawback, we propose in this work a multi-modal triplet loss (MMTL) which utilizes multimodal information to search a disen…
We study the problem of building models that disentangle independent factors of variation. Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis. As data we use a weakly labeled training set. Our weak labels indicate what single factor has changed between two data samples, although the relative value of the change is unknown. This labeling is of particular interest as it may be readily available without annotation costs. To make use of weak labels we introduce an autoencoder model and …
The auto-encoder method is a type of dimensionality reduction method. A mapping from a vector to a descriptor that represents essential information can be automatically generated from a set of vectors without any supervising information. However, an image and its spatially shifted version are encoded into different descriptors by an existing ordinary auto-encoder because each descriptor includes a spatial subpattern and its position. To generate a descriptor representing a spatial subpattern in an image, we need to normalize its spatial position in the images prior to training an ordinary auto…
China University of Petroleum(East China)（中国石油大学（华东））
Scale-space representation has been popular in computer vision community due to its theoretical foundation. The motivation for generating a scale-space representation of a given data set originates from the basic observation that real-world objects are composed of different structures at different scales. Hence, it's reasonable to consider learning features with image pyramids generated by smoothing and down-sampling operations. In this paper we propose Laplacian pyramid auto-encoders, a straightforward modification of the deep convolutional auto-encoder architecture, for unsupervised represen…
