We present a new latent model of natural images that can be learned on large-scale datasets. The learning process provides a latent embedding for every image in the training dataset, as well as a deep convolutional network that maps the latent space to the image space. After training, the new model provides a strong and universal image prior for a variety of image restoration tasks such as large-hole inpainting, superresolution, and colorization. To model high-resolution natural images, our approach uses latent spaces of very high dimensionality (one to two orders of magnitude higher than previous latent image models). To tackle this high dimensionality, we use latent spaces with a special manifold structure (convolutional manifolds) parameterized by a ConvNet of a certain architecture. In the experiments, we compare the learned latent models with latent models learned by autoencoders, advanced variants of generative adversarial networks, and a strong baseline system using simpler parameterization of the latent space. Our model outperforms the competing approaches over a range of restoration tasks.
Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a coarse map of salient features in an image, which rarely tells the whole story of what a convolutional neural network (CNN) learned. Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). Our GAN framework disentangles lung structure from COVID-19 features. Using this GAN, we c…
We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the latent space of StyleGAN, from which the optimal compression is learned. To do so, a diffeomorphic latent representation is learned using a normalizing flows model, where an entropy model can be optimized for image coding. In addition, we propose a new perceptual loss that is more efficient than other counterparts. Finally, an entropy model for video inter coding…
There exist many forms of deep latent variable models, such as the variational autoencoder and adversarial autoencoder. Regardless of the specific class of model, there exists an implicit consensus that the latent distribution should be regularized towards the prior, even in the case where the prior distribution is learned. Upon investigating the effect of latent regularization on image generation our results indicate that in the case where a sufficiently expressive prior is learned, latent regularization is not necessary and may in fact be harmful insofar as image quality is concerned. We add…
The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-dimensional latent vectors to high-dimensional data while encouraging a global structure in the latent space through the use of a specified prior distribution. When this prior does not match the structure of the true data manifold, it can lead to a less accurate model of the data. To resolve this mismatch, we introduce the Variational Autoencoder with Learned Latent Structure (…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所IIS）
This report to our stage 2 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for learning disentangled latent factors. We propose to train a variational autoencoder on regionally aggregated feature maps obtained from networks pretrained on the ImageNet database, utilizing the implicit inductive bias contained in those features for disentanglement. This bias can be further enhanced by explicitly fine-tuning the feature maps on auxiliary tasks useful for the challenge, such as angle, position estimation, or color classification. Our approach ac…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
We propose a latent space energy-based prior model for text generation and classification. The model stands on a generator network that generates the text sequence based on a continuous latent vector. The energy term of the prior model couples a continuous latent vector and a symbolic one-hot vector, so that discrete category can be inferred from the observed example based on the continuous latent vector. Such a latent space coupling naturally enables incorporation of information bottleneck regularization to encourage the continuous latent vector to extract information from the observed exampl…
Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point optimization problem, interpreted as an adversarial game between a generator and a discriminator functions; and parameterizing the generator and the discriminator as deep convolutional neural networks. The goal of this paper is to disentangle the contribution of these two factors to the success of GANs. In particular, we introduce Generative Latent Optimization (GLO), …
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Google Brain（谷歌大脑）
Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks. Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions of image and latent vector pairs. We generalize these approaches to incorporate multiple layers of feedback on reconstructions, self-supervision, and other forms of supervision based on prior or learned knowledge about the desired solutions. We achieve …
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model. We use this property, applying fully convolutional models to lossless compression, demonstrating a method to scale the VAE-based 'Bits-Back with ANS' algorithm for lossless compression to large color photographs, and achieving state of the art for compression of full size ImageNet images. We release Craystack, an open source library for convenient prototyping of lossless compression using pr…
Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images
Department of Computer Science, Georgia State University（计算机科学系，佐治亚州立大学）；Department of Electrical and Computer Engineering, Marquette University（电气与计算机工程系，马基特大学）；Joint Dept. of Biomedical Eng., Marquette Univ. and Med. Coll. of Wisconsin（马基特大学与威斯康星医学院联合生物医学工程系）
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation. However, discrete latent spaces need to be sufficiently large to capture the complexities of real-world data, rendering downstream tasks computationally challenging. For instance, performing motion planning in a high-dimensional latent representation of the environment could be intractable. We consider the problem of sparsifying the discrete latent space of a…
University of California, Los Angeles（加州大学洛杉矶分校）；Stevens Institute of Technology（斯蒂文斯理工学院）
We propose to learn energy-based model (EBM) in the latent space of a generator model, so that the EBM serves as a prior model that stands on the top-down network of the generator model. Both the latent space EBM and the top-down network can be learned jointly by maximum likelihood, which involves short-run MCMC sampling from both the prior and posterior distributions of the latent vector. Due to the low dimensionality of the latent space and the expressiveness of the top-down network, a simple EBM in latent space can capture regularities in the data effectively, and MCMC sampling in latent sp…
LatentQGAN: A Hybrid QGAN with Classical Convolutional Autoencoder
Université de Sherbrooke（谢布鲁克大学）；Polytechnique Montréal（蒙特利尔理工学院）；Thales Digital Solutions（泰雷兹数字解决方案公司）；Institut Quantique, Université de Sherbrooke（谢布鲁克大学量子研究所）
Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow multiple renditions of the same sentence via sampling. The degree of prosodic variability depends heavily on the prior that is used when sampling. In this paper, we propose a novel method to compute an informative prior for the VAE latent space of a neural text-to-speech (TTS) system. By doing so, we aim to sample with more prosodic variability, while gaining controllability over the latent space's structure. By using as…
School of Computer Science and Technology（计算机科学与技术学院）
Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be vulnerable to the structural attacks and noises. To address this issue, we propose a novel Latent Graph Convolutional Representation (LatGCR) for robust graph data representation and learning. Our LatGCR is derived based on reformulating graph convolutional representation from the aspect of graph neighborhood reconstruction. Given an input graph $\textbf{A}$, Lat…
Performance of fingerprint recognition depends heavily on the extraction of minutiae points. Enhancement of the fingerprint ridge pattern is thus an essential pre-processing step that noticeably reduces false positive and negative detection rates. A particularly challenging setting is when the fingerprint images are corrupted or partially missing. In this work, we apply generative convolutional networks to denoise visible minutiae and predict the missing parts of the ridge pattern. The proposed enhancement approach is tested as a pre-processing step in combination with several standard feature…
In this paper, we propose a novel learning based method for automated segmenta-tion of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton fea-tures are used to classify the MRI image voxels. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI train-ing dataset using the FCN. The learned features are then applied to random for-ests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 …
Key Laboratory of Machine Perception (MOE), School of EECS, Peking University（北京大学信息科学技术学院机器感知与智能教育部重点实验室）
Minutiae play a major role in fingerprint identification. Extracting reliable minutiae is difficult for latent fingerprints which are usually of poor quality. As the limitation of traditional handcrafted features, a fully convolutional network (FCN) is utilized to learn features directly from data to overcome complex background noises. Raw fingerprints are mapped to a correspondingly-sized minutia-score map with a fixed stride. And thus a large number of minutiae will be extracted through a given threshold. Then small regions centering at these minutia points are entered into a convolutional n…
University of Maryland, College Park（马里兰大学帕克分校）；Google Research（谷歌研究院）
Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs). However, unsupervised representations learned by VAEs are significantly outperformed by those learned by supervised learning for recognition. Our hypothesis is that to learn useful representations for recognition the model needs to be encouraged to learn about repeating and consistent patterns in data. Drawing inspiration from the mid-level representation disco…
Since Convolutional Neural Networks (ConvNets) are able to simultaneously learn features and classifiers to discriminate different categories of activities, recent works have employed ConvNets approaches to perform human activity recognition (HAR) based on wearable sensors, allowing the removal of expensive human work and expert knowledge. However, these approaches have their power of discrimination limited mainly by the large number of parameters that compose the network and the reduced number of samples available for training. Inspired by this, we propose an accurate and robust approach, ref…
Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic explanations about the learned representation is challenging without direct supervision to produce such explanations. We propose a general framework, Latent Visual Semantic Explainer (LaViSE), to teach any existing convolutional neural network to generate text descriptions about its own latent representations at the filter level. Our method constructs a mapping between the visual and semantic spaces using generic image …
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the representation is usually uninterpretable, making analysis and principled progress challenging. We propose a framework, called latent responses, which exploits the locally contractive behavior exhibited by variational autoencoders to explore the learned manifold. More specifically, we develop tools to probe the representation using interventions in the latent spac…
Samsung AI Center（三星人工智能中心）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）
We propose a neural head reenactment system, which is driven by a latent pose representation and is capable of predicting the foreground segmentation alongside the RGB image. The latent pose representation is learned as a part of the entire reenactment system, and the learning process is based solely on image reconstruction losses. We show that despite its simplicity, with a large and diverse enough training dataset, such learning successfully decomposes pose from identity. The resulting system can then reproduce mimics of the driving person and, furthermore, can perform cross-person reenactme…
This work details Sighthounds fully automated license plate detection and recognition system. The core technology of the system is built using a sequence of deep Convolutional Neural Networks (CNNs) interlaced with accurate and efficient algorithms. The CNNs are trained and fine-tuned so that they are robust under different conditions (e.g. variations in pose, lighting, occlusion, etc.) and can work across a variety of license plate templates (e.g. sizes, backgrounds, fonts, etc). For quantitative analysis, we show that our system outperforms the leading license plate detection and recognition…
Depth estimation from a single image is a fundamental problem in computer vision. In this paper, we propose a simple yet effective convolutional spatial propagation network (CSPN) to learn the affinity matrix for depth prediction. Specifically, we adopt an efficient linear propagation model, where the propagation is performed with a manner of recurrent convolutional operation, and the affinity among neighboring pixels is learned through a deep convolutional neural network (CNN). We apply the designed CSPN to two depth estimation tasks given a single image: (1) To refine the depth output from s…
Samsung R&D Institute India- Bangalore（三星印度班加罗尔研发中心）；Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）；TensorTour Inc.（TensorTour公司）
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zero-shot quantization that does not require original unlabelled training samples of a given task. These best-published works heavily rely on the learned batch normalization (BN) parameters to infer the range of the activations for quantization. In particular, these methods are built upon either empirical estimation framework or the data distillation approach, for computing the ra…
National Taiwan University（台湾大学）；Soochow University（东吴大学）
Candlesticks are graphical representations of price movements for a given period. The traders can discovery the trend of the asset by looking at the candlestick patterns. Although deep convolutional neural networks have achieved great success for recognizing the candlestick patterns, their reasoning hides inside a black box. The traders cannot make sure what the model has learned. In this contribution, we provide a framework which is to explain the reasoning of the learned model determining the specific candlestick patterns of time series. Based on the local search adversarial attacks, we show…
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features. Specifically, we utilize deep architectures to learn discriminative convolutional feature maps, and conduct trajectory-constrained pooling to aggregate these convolutional features into effective descriptors. To enhance the robustness of TDDs, we design two normalization methods to transform convolutional feature maps, namely…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
Neural network weights are typically initialized at random from univariate distributions, controlling just the variance of individual weights even in highly-structured operations like convolutions. Recent ViT-inspired convolutional networks such as ConvMixer and ConvNeXt use large-kernel depthwise convolutions whose learned filters have notable structure; this presents an opportunity to study their empirical covariances. In this work, we first observe that such learned filters have highly-structured covariance matrices, and moreover, we find that covariances calculated from small networks may …
Deep Neural Networks - especially Convolutional Neural Network (ConvNet) has become the state-of-the-art for image classification, pattern recognition and various computer vision tasks. ConvNet has a huge potential in medical domain for analyzing medical data to diagnose diseases in an efficient way. Based on extracted features by ConvNet model from MRI data, early diagnosis is very crucial for preventing progress and treating the Alzheimer's disease. Despite having the ability to deliver great performance, absence of interpretability of the model's decision can lead to misdiagnosis which can …
CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification
Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata, IEM Centre of Excellence for InnovAI, Department of Computer Science & Engineering（工程管理学院（IEM）、工程管理大学科塔卡尔，创新AI研究中心、计算机科学与工程系）；Institute of Engineering and Management (IEM), University of Engineering and Management Kolkata, Department of Computer Science & Engineering（工程管理学院（IEM）、工程管理大学科塔卡尔，计算机科学与工程系）
Seoul National University（首尔国立大学）；Hanyang University（汉阳大学）；University of Birmingham（伯明翰大学）
We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture. In order to prevent the numer…
In this paper we explore tying together the ideas from Scattering Transforms and Convolutional Neural Networks (CNN) for Image Analysis by proposing a learnable ScatterNet. Previous attempts at tying them together in hybrid networks have tended to keep the two parts separate, with the ScatterNet forming a fixed front end and a CNN forming a learned backend. We instead look at adding learning between scattering orders, as well as adding learned layers before the ScatterNet. We do this by breaking down the scattering orders into single convolutional-like layers we call 'locally invariant' layers…
Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work proposes a guided learning approach with an additional concept layer in a CNN- based architecture to learn the associations between visual features and word phrases. We design an objective function that optimizes both prediction accuracy and semantics of the learned feature representations. Experiment results demonstrate that the proposed model can learn concepts…
Center for Neural Science（神经科学中心）；New York University（纽约大学）；Department of Psychology and Center for Data Science（心理学系与数据科学中心）
Modern deep neural networks require a tremendous amount of data to train, often needing hundreds or thousands of labeled examples to learn an effective representation. For these networks to work with less data, more structure must be built into their architectures or learned from previous experience. The learned weights of convolutional neural networks (CNNs) trained on large datasets for object recognition contain a substantial amount of structure. These representations have parallels to simple cells in the primary visual cortex, where receptive fields are smooth and contain many regularities…
Mercedes-Benz AG（梅赛德斯-奔驰股份公司）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Research Center for Information Technology（信息技术研究中心）
Judging the quality of samples synthesized by generative models can be tedious and time consuming, especially for complex data structures, such as point clouds. This paper presents a novel approach to quantify the realism of local regions in LiDAR point clouds. Relevant features are learned from real-world and synthetic point clouds by training on a proxy classification task. Inspired by fair networks, we use an adversarial technique to discourage the encoding of dataset-specific information. The resulting metric can assign a quality score to samples without requiring any task specific annotat…
University of California, Berkeley（加州大学伯克利分校）；Tsinghua University（清华大学）
Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However, existing end-to-end approaches are often lack of interpretability, and can only deal with simple driving tasks like lane keeping. In this paper, we propose an interpretable deep reinforcement learning method for end-to-end autonomous driving, which is able to handle complex urban scenarios. A sequential latent environment model is introduced and learned joint…
University of Science and Technology of China（中国科学技术大学）
Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then decode them for reconstruction purposes. To capture spatial dependencies in the latent space, prior works exploit hyperprior and spatial context model to build an entropy model, which estimates the bit-rate for end-to-end rate-distortion optimization. However, such an entropy model is suboptimal from two aspects: (1) It fails to capture spatial…
Hong Kong University of Science and Technology（香港科技大学）
Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when the crowd size grows. We suggest that this can be addressed by enabling the network to identify and pay attention to the humans in the crowd that are most critical to navigation. We propose a novel network utilizing a graph representation to learn the policy. We first train a graph convolutional network based on human gaze data that accurately predicts human a…
