PyTorchKR Papers

최신 논문

총 2,994편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2203.15321

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

arXiv:2203.15406

TransductGAN: a Transductive Adversarial Model for Novelty Detection

Novelty detection, a widely studied problem in machine learning, is the problem of detecting a novel class of data that has not been previously observed. A common setting for novelty detection is inductive whereby only examples of the negative class are available during training time. Transductive novelty detection on the other hand has only witnessed a recent surge in interest, it not only makes use of the negative class during training but also incorporates the (unlabeled) test set to detect novel examples. Several studies have emerged under the transductive setting umbrella that have demonstrated its advantage over its inductive counterpart. Depending on the assumptions about the data, these methods go by different names (e.g. transductive novelty detection, semi-supervised novelty detection, positive-unlabeled learning, out-of-distribution detection). With the use of generative adversarial networks (GAN), a segment of those studies have adopted a transductive setup in order to learn how to generate examples of the novel class. In this study, we propose TransductGAN, a transductive generative adversarial network that attempts to learn how to generate image examples from both the novel and negative classes by using a mixture of two Gaussians in the latent space. It achieves that by incorporating an adversarial autoencoder with a GAN network, the ability to generate examples of novel data points offers not only a visual representation of novelties, but also overcomes the hurdle faced by many inductive methods of how to tune the model hyperparameters at the decision rule level. Our model has shown superior performance over state-of-the-art inductive and transductive methods. Our study is fully reproducible with the code available publicly.

arXiv:2203.15347공식 코드 · Papers with Code

Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

Synthesizing a subject-specific pathology-free image from a pathological image is valuable for algorithm development and clinical practice. In recent years, several approaches based on the Generative Adversarial Network (GAN) have achieved promising results in pseudo-healthy synthesis. However, the discriminator (i.e., a classifier) in the GAN cannot accurately identify lesions and further hampers from generating admirable pseudo-healthy images. To address this problem, we present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. Then, we apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem existing in medical image segmentation. Furthermore, a reliable metric is proposed by utilizing two attributes of label noise to measure the health of synthetic images. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods. The method achieves better performance than the existing methods with only 30\% of the training data. The effectiveness of the proposed method is also demonstrated on the LiTS and the T1 modality of BraTS. The code and the pre-trained model of this study are publicly available at https://github.com/Au3C2/Generator-Versus-Segmentor.

arXiv:2203.15149공식 코드 · Papers with Code

CMGAN: Conformer-based Metric GAN for Speech Enhancement

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech signal. In this paper, we propose a conformer-based metric generative adversarial network (CMGAN) for SE in the time-frequency (TF) domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information by modeling both time and frequency dependencies. The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech. In addition, a metric discriminator is employed to further improve the quality of the enhanced estimated speech by optimizing the generator with respect to a corresponding evaluation score. Quantitative analysis on Voice Bank+DEMAND dataset indicates the capability of CMGAN in outperforming various previous models with a margin, i.e., PESQ of 3.41 and SSNR of 11.10 dB.

arXiv:2203.15640

Synthesis and Execution of Communicative Robotic Movements with Generative Adversarial Networks

Object manipulation is a natural activity we perform every day. How humans handle objects can communicate not only the willfulness of the acting, or key aspects of the context where we operate, but also the properties of the objects involved, without any need for explicit verbal description. Since human intelligence comprises the ability to read the context, allowing robots to perform actions that intuitively convey this kind of information would greatly facilitate collaboration. In this work, we focus on how to transfer on two different robotic platforms the same kinematics modulation that humans adopt when manipulating delicate objects, aiming to endow robots with the capability to show carefulness in their movements. We choose to modulate the velocity profile adopted by the robots' end-effector, inspired by what humans do when transporting objects with different characteristics. We exploit a novel Generative Adversarial Network architecture, trained with human kinematics examples, to generalize over them and generate new and meaningful velocity profiles, either associated with careful or not careful attitudes. This approach would allow next generation robots to select the most appropriate style of movement, depending on the perceived context, and autonomously generate their motor action execution.

arXiv:2203.13856공식 코드 · Papers with Code

Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization

Deep learning applications for assessing medical images are limited because the datasets are often small and imbalanced. The use of synthetic data has been proposed in the literature, but neither a robust comparison of the different methods nor generalizability has been reported. Our approach integrates a retinal image quality assessment model and StyleGAN2 architecture to enhance Age-related Macular Degeneration (AMD) detection capabilities and improve generalizability. This work compares ten different Generative Adversarial Network (GAN) architectures to generate synthetic eye-fundus images with and without AMD. We combined subsets of three public databases (iChallenge-AMD, ODIR-2019, and RIADD) to form a single training and test set. We employed the STARE dataset for external validation, ensuring a comprehensive assessment of the proposed approach. The results show that StyleGAN2 reached the lowest Frechet Inception Distance (166.17), and clinicians could not accurately differentiate between real and synthetic images. ResNet-18 architecture obtained the best performance with 85% accuracy and outperformed the two human experts (80% and 75%) in detecting AMD fundus images. The accuracy rates were 82.8% for the test set and 81.3% for the STARE dataset, demonstrating the model's generalizability. The proposed methodology for synthetic medical image generation has been validated for robustness and accuracy, with free access to its code for further research and development in this field.

arXiv:2203.14074

V3GAN: Decomposing Background, Foreground and Motion for Video Generation

Video generation is a challenging task that requires modeling plausible spatial and temporal dynamics in a video. Inspired by how humans perceive a video by grouping a scene into moving and stationary components, we propose a method that decomposes the task of video generation into the synthesis of foreground, background and motion. Foreground and background together describe the appearance, whereas motion specifies how the foreground moves in a video over time. We propose V3GAN, a novel three-branch generative adversarial network where two branches model foreground and background information, while the third branch models the temporal information without any supervision. The foreground branch is augmented with our novel feature-level masking layer that aids in learning an accurate mask for foreground and background separation. To encourage motion consistency, we further propose a shuffling loss for the video discriminator. Extensive quantitative and qualitative analysis on synthetic as well as real-world benchmark datasets demonstrates that V3GAN outperforms the state-of-the-art methods by a significant margin.

arXiv:2203.13607

Fast and computationally efficient generative adversarial network algorithm for unmanned aerial vehicle-based network coverage optimization

The challenge of dynamic traffic demand in mobile networks is tackled by moving cells based on unmanned aerial vehicles. Considering the tremendous potential of unmanned aerial vehicles in the future, we propose a new heuristic algorithm for coverage optimization. The proposed algorithm is implemented based on a conditional generative adversarial neural network, with a unique multilayer sum-pooling loss function. To assess the performance of the proposed approach, we compare it with the optimal core-set algorithm and quasi-optimal spiral algorithm. Simulation results show that the proposed approach converges to the quasi-optimal solution with a negligible difference from the global optimum while maintaining a quadratic complexity regardless of the number of users.

arXiv:2203.13441

3D GAN Inversion for Controllable Portrait Image Animation

Millions of images of human faces are captured every single day; but these photographs portray the likeness of an individual with a fixed pose, expression, and appearance. Portrait image animation enables the post-capture adjustment of these attributes from a single image while maintaining a photorealistic reconstruction of the subject's likeness or identity. Still, current methods for portrait image animation are typically based on 2D warping operations or manipulations of a 2D generative adversarial network (GAN) and lack explicit mechanisms to enforce multi-view consistency. Thus these methods may significantly alter the identity of the subject, especially when the viewpoint relative to the camera is changed. In this work, we leverage newly developed 3D GANs, which allow explicit control over the pose of the image subject with multi-view consistency. We propose a supervision strategy to flexibly manipulate expressions with 3D morphable models, and we show that the proposed method also supports editing appearance attributes, such as age or hairstyle, by interpolating within the latent space of the GAN. The proposed technique for portrait image animation outperforms previous methods in terms of image quality, identity preservation, and pose transfer while also supporting attribute editing.

arXiv:2203.12297공식 코드 · Papers with Code

Increasing the accuracy and resolution of precipitation forecasts using deep generative models

Accurately forecasting extreme rainfall is notoriously difficult, but is also ever more crucial for society as climate change increases the frequency of such extremes. Global numerical weather prediction models often fail to capture extremes, and are produced at too low a resolution to be actionable, while regional, high-resolution models are hugely expensive both in computation and labour. In this paper we explore the use of deep generative models to simultaneously correct and downscale (super-resolve) global ensemble forecasts over the Continental US. Specifically, using fine-grained radar observations as our ground truth, we train a conditional Generative Adversarial Network -- coined CorrectorGAN -- via a custom training procedure and augmented loss function, to produce ensembles of high-resolution, bias-corrected forecasts based on coarse, global precipitation forecasts in addition to other relevant meteorological fields. Our model outperforms an interpolation baseline, as well as super-resolution-only and CNN-based univariate methods, and approaches the performance of an operational regional high-resolution model across an array of established probabilistic metrics. Crucially, CorrectorGAN, once trained, produces predictions in seconds on a single machine. These results raise exciting questions about the necessity of regional models, and whether data-driven downscaling and correction methods can be transferred to data-poor regions that so far have had no access to high-resolution forecasts.

arXiv:2203.11363공식 코드 · Papers with Code

PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations

We propose a new class of physics-informed neural networks, called physics-informed Variational Autoencoder (PI-VAE), to solve stochastic differential equations (SDEs) or inverse problems involving SDEs. In these problems the governing equations are known but only a limited number of measurements of system parameters are available. PI-VAE consists of a variational autoencoder (VAE), which generates samples of system variables and parameters. This generative model is integrated with the governing equations. In this integration, the derivatives of VAE outputs are readily calculated using automatic differentiation, and used in the physics-based loss term. In this work, the loss function is chosen to be the Maximum Mean Discrepancy (MMD) for improved performance, and neural network parameters are updated iteratively using the stochastic gradient descent algorithm. We first test the proposed method on approximating stochastic processes. Then we study three types of problems related to SDEs: forward and inverse problems together with mixed problems where system parameters and solutions are simultaneously calculated. The satisfactory accuracy and efficiency of the proposed method are numerically demonstrated in comparison with physics-informed generative adversarial network (PI-WGAN).

arXiv:2203.11632

QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation

This paper studies the task of conditional Human Motion Animation (cHMA). Given a source image and a driving video, the model should animate the new frame sequence, in which the person in the source image should perform a similar motion as the pose sequence from the driving video. Despite the success of Generative Adversarial Network (GANs) methods in image and video synthesis, it is still very challenging to conduct cHMA due to the difficulty in efficiently utilizing the conditional guided information such as images or poses, and generating images of good visual quality. To this end, this paper proposes a novel model of learning to Quantize, Scrabble, and Craft (QS-Craft) for conditional human motion animation. The key novelties come from the newly introduced three key steps: quantize, scrabble and craft. Particularly, our QS-Craft employs transformer in its structure to utilize the attention architectures. The guided information is represented as a pose coordinate sequence extracted from the driving videos. Extensive experiments on human motion datasets validate the efficacy of our model.

arXiv:2203.11305공식 코드 · Papers with Code

Generative Adversarial Network for Future Hand Segmentation from Egocentric Video

We introduce the novel problem of anticipating a time series of future hand masks from egocentric video. A key challenge is to model the stochasticity of future head motions, which globally impact the head-worn camera video analysis. To this end, we propose a novel deep generative model -- EgoGAN, which uses a 3D Fully Convolutional Network to learn a spatio-temporal video representation for pixel-wise visual anticipation, generates future head motion using Generative Adversarial Network (GAN), and then predicts the future hand masks based on the video representation and the generated future head motion. We evaluate our method on both the EPIC-Kitchens and the EGTEA Gaze+ datasets. We conduct detailed ablation studies to validate the design choices of our approach. Furthermore, we compare our method with previous state-of-the-art methods on future image segmentation and show that our method can more accurately predict future hand masks.

arXiv:2203.11570

Conditional Generative Data Augmentation for Clinical Audio Datasets

In this work, we propose a novel data augmentation method for clinical audio datasets based on a conditional Wasserstein Generative Adversarial Network with Gradient Penalty (cWGAN-GP), operating on log-mel spectrograms. To validate our method, we created a clinical audio dataset which was recorded in a real-world operating room during Total Hip Arthroplasty (THA) procedures and contains typical sounds which resemble the different phases of the intervention. We demonstrate the capability of the proposed method to generate realistic class-conditioned samples from the dataset distribution and show that training with the generated augmented samples outperforms classical audio augmentation methods in terms of classification performance. The performance was evaluated using a ResNet-18 classifier which shows a mean Macro F1-score improvement of 1.70% in a 5-fold cross validation experiment using the proposed augmentation method. Because clinical data is often expensive to acquire, the development of realistic and high-quality data augmentation methods is crucial to improve the robustness and generalization capabilities of learning-based algorithms which is especially important for safety-critical medical applications. Therefore, the proposed data augmentation method is an important step towards improving the data bottleneck for clinical audio-based machine learning systems.

arXiv:2203.10348

Font Generation with Missing Impression Labels

Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels. The main difficulty is that font impression is ambiguous and the absence of an impression label does not always mean that the font does not have the impression. This paper proposes a font generation model that is robust against missing impression labels. The key ideas of the proposed method are (1)a co-occurrence-based missing label estimator and (2)an impression label space compressor. The first is to interpolate missing impression labels based on the co-occurrence of labels in the dataset and use them for training the model as completed label conditions. The second is an encoder-decoder module to compress the high-dimensional impression space into low-dimensional. We proved that the proposed model generates high-quality font images using multi-label data with missing labels through qualitative and quantitative evaluations.

arXiv:2203.10307

Modelling nonlinear dependencies in the latent space of inverse scattering

The problem of inverse scattering proposed by Angles and Mallat in 2018, concerns training a deep neural network to invert the scattering transform applied to an image. After such a network is trained, it can be used as a generative model given that we can sample from the distribution of principal components of scattering coefficients. For this purpose, Angles and Mallat simply use samples from independent Gaussians. However, as shown in this paper, the distribution of interest can actually be very far from normal and non-negligible dependencies might exist between different coefficients. This motivates using models for this distribution that allow for non-linear dependencies between variables. Within this paper, two such models are explored, namely a Variational AutoEncoder and a Generative Adversarial Network. We demonstrate the results obtained can be extremely realistic on some datasets and look better than those produced by Angles and Mallat. The conducted meta-analysis also shows a clear practical advantage of such constructed generative models in terms of the efficiency of their training process compared to existing generative models for images.

arXiv:2203.11105공식 코드 · Papers with Code

High-fidelity GAN Inversion with Padding Space

Inverting a Generative Adversarial Network (GAN) facilitates a wide range of image editing tasks using pre-trained generators. Existing methods typically employ the latent space of GANs as the inversion space yet observe the insufficient recovery of spatial details. In this work, we propose to involve the padding space of the generator to complement the latent space with spatial information. Concretely, we replace the constant padding (e.g., usually zeros) used in convolution layers with some instance-aware coefficients. In this way, the inductive bias assumed in the pre-trained model can be appropriately adapted to fit each individual image. Through learning a carefully designed encoder, we manage to improve the inversion quality both qualitatively and quantitatively, outperforming existing alternatives. We then demonstrate that such a space extension barely affects the native GAN manifold, hence we can still reuse the prior knowledge learned by GANs for various downstream applications. Beyond the editing tasks explored in prior arts, our approach allows a more flexible image manipulation, such as the separate control of face contour and facial details, and enables a novel editing manner where users can customize their own manipulations highly efficiently.

arXiv:2203.09362

Fine Detailed Texture Learning for 3D Meshes with Generative Models

This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network. In the generative learning pipeline, we propose two improvements. First, since the learned textures should be spatially aligned, we propose an attention mechanism that relies on the learnable positions of pixels. Secondly, since discriminator receives aligned texture maps, we augment its input with a learnable embedding which improves the feedback to the generator. We achieve significant improvements on multi-view sequences from Tripod dataset as well as on single-view image datasets, Pascal 3D+ and CUB. We demonstrate that our method achieves superior 3D textured models compared to the previous works. Please visit our web-page for 3D visuals.

arXiv:2203.08289

Driving Anomaly Detection Using Conditional Generative Adversarial Network

Anomaly driving detection is an important problem in advanced driver assistance systems (ADAS). It is important to identify potential hazard scenarios as early as possible to avoid potential accidents. This study proposes an unsupervised method to quantify driving anomalies using a conditional generative adversarial network (GAN). The approach predicts upcoming driving scenarios by conditioning the models on the previously observed signals. The system uses the difference of the output from the discriminator between the predicted and actual signals as a metric to quantify the anomaly degree of a driving segment. We take a driver-centric approach, considering physiological signals from the driver and controller area network-Bus (CAN-Bus) signals from the vehicle. The approach is implemented with convolutional neural networks (CNNs) to extract discriminative feature representations, and with long short-term memory (LSTM) cells to capture temporal information. The study is implemented and evaluated with the driving anomaly dataset (DAD), which includes 250 hours of naturalistic recordings manually annotated with driving events. The experimental results reveal that recordings annotated with events that are likely to be anomalous, such as avoiding on-road pedestrians and traffic rule violations, have higher anomaly scores than recordings without any event annotation. The results are validated with perceptual evaluations, where annotators are asked to assess the risk and familiarity of the videos detected with high anomaly scores. The results indicate that the driving segments with higher anomaly scores are more risky and less regularly seen on the road than other driving segments, validating the proposed unsupervised approach.

arXiv:2203.07897공식 코드 · Papers with Code

Magnetic Field Prediction Using Generative Adversarial Networks

Plenty of scientific and real-world applications are built on magnetic fields and their characteristics. To retrieve the valuable magnetic field information in high resolution, extensive field measurements are required, which are either time-consuming to conduct or even not feasible due to physical constraints. To alleviate this problem, we predict magnetic field values at a random point in space from a few point measurements by using a generative adversarial network (GAN) structure. The deep learning (DL) architecture consists of two neural networks: a generator, which predicts missing field values of a given magnetic field, and a critic, which is trained to calculate the statistical distance between real and generated magnetic field distributions. By minimizing this statistical distance, a reconstruction loss as well as physical losses, our trained generator has learned to predict the missing field values with a median reconstruction test error of 5.14%, when a single coherent region of field points is missing, and 5.86%, when only a few point measurements in space are available and the field measurements around are predicted. We verify the results on an experimentally validated field.