PyTorchKR Papers

최신 논문

총 2,994편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2304.10382

Conditional Generative Models for Learning Stochastic Processes

A framework to learn a multi-modal distribution is proposed, denoted as the Conditional Quantum Generative Adversarial Network (C-qGAN). The neural network structure is strictly within a quantum circuit and, as a consequence, is shown to represent a more efficient state preparation procedure than current methods. This methodology has the potential to speed-up algorithms, such as Monte Carlo analysis. In particular, after demonstrating the effectiveness of the network in the learning task, the technique is applied to price Asian option derivatives, providing the foundation for further research on other path-dependent options.

arXiv:2304.09384

SP-BatikGAN: An Efficient Generative Adversarial Network for Symmetric Pattern Generation

Following the contention of AI arts, our research focuses on bringing AI for all, particularly for artists, to create AI arts with limited data and settings. We are interested in geometrically symmetric pattern generation, which appears on many artworks such as Portuguese, Moroccan tiles, and Batik, a cultural heritage in Southeast Asia. Symmetric pattern generation is a complex problem, with prior research creating too-specific models for certain patterns only. We provide publicly, the first-ever 1,216 high-quality symmetric patterns straight from design files for this task. We then formulate symmetric pattern enforcement (SPE) loss to leverage underlying symmetric-based structures that exist on current image distributions. Our SPE improves and accelerates training on any GAN configuration, and, with efficient attention, SP-BatikGAN compared to FastGAN, the state-of-the-art GAN for limited setting, improves the FID score from 110.11 to 90.76, an 18% decrease, and model diversity recall score from 0.047 to 0.204, a 334% increase.

arXiv:2304.09376

Physical Knowledge Enhanced Deep Neural Network for Sea Surface Temperature Prediction

Traditionally, numerical models have been deployed in oceanography studies to simulate ocean dynamics by representing physical equations. However, many factors pertaining to ocean dynamics seem to be ill-defined. We argue that transferring physical knowledge from observed data could further improve the accuracy of numerical models when predicting Sea Surface Temperature (SST). Recently, the advances in earth observation technologies have yielded a monumental growth of data. Consequently, it is imperative to explore ways in which to improve and supplement numerical models utilizing the ever-increasing amounts of historical observational data. To this end, we introduce a method for SST prediction that transfers physical knowledge from historical observations to numerical models. Specifically, we use a combination of an encoder and a generative adversarial network (GAN) to capture physical knowledge from the observed data. The numerical model data is then fed into the pre-trained model to generate physics-enhanced data, which can then be used for SST prediction. Experimental results demonstrate that the proposed method considerably enhances SST prediction performance when compared to several state-of-the-art baselines.

arXiv:2304.09626

StyleDEM: a Versatile Model for Authoring Terrains

Many terrain modelling methods have been proposed for the past decades, providing efficient and often interactive authoring tools. However, they generally do not include any notion of style, which is a critical aspect for designers in the entertainment industry. We introduce StyleDEM, a new generative adversarial network method for terrain synthesis and authoring, with a versatile toolbox of authoring methods with style. This method starts from an input sketch or an existing terrain. It outputs a terrain with features that can be authored using interactive brushes and enhanced with additional tools such as style manipulation or super-resolution. The strength of our approach resides in the versatility and interoperability of the toolbox.

arXiv:2304.08665

Insta(nt) Pet Therapy: GAN-generated Images for Therapeutic Social Media Content

The positive therapeutic effect of viewing pet images online has been well-studied. However, it is difficult to obtain large-scale production of such content since it relies on pet owners to capture photographs and upload them. I use a Generative Adversarial Network-based framework for the creation of fake pet images at scale. These images are uploaded on an Instagram account where they drive user engagement at levels comparable to those seen with images from accounts with traditional pet photographs, underlining the applicability of the framework to be used for pet-therapy social media content.

arXiv:2304.08072

Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism

Multimodal magnetic resonance imaging (MRI) can reveal different patterns of human tissue and is crucial for clinical diagnosis. However, limited by cost, noise and manual labeling, obtaining diverse and reliable multimodal MR images remains a challenge. For the same lesion, different MRI manifestations have great differences in background information, coarse positioning and fine structure. In order to obtain better generation and segmentation performance, a coordination-spatial attention generation adversarial network (CASP-GAN) based on the cycle-consistent generative adversarial network (CycleGAN) is proposed. The performance of the generator is optimized by introducing the Coordinate Attention (CA) module and the Spatial Attention (SA) module. The two modules can make full use of the captured location information, accurately locating the interested region, and enhancing the generator model network structure. The ability to extract the structure information and the detailed information of the original medical image can help generate the desired image with higher quality. There exist some problems in the original CycleGAN that the training time is long, the parameter amount is too large, and it is difficult to converge. In response to this problem, we introduce the Coordinate Attention (CA) module to replace the Res Block to reduce the number of parameters, and cooperate with the spatial information extraction network above to strengthen the information extraction ability. On the basis of CASP-GAN, an attentional generative cross-modality segmentation (AGCMS) method is further proposed. This method inputs the modalities generated by CASP-GAN and the real modalities into the segmentation network for brain tumor segmentation. Experimental results show that CASP-GAN outperforms CycleGAN and some state-of-the-art methods in PSNR, SSMI and RMSE in most tasks.

arXiv:2304.07721

A Novel end-to-end Framework for Occluded Pixel Reconstruction with Spatio-temporal Features for Improved Person Re-identification

Person re-identification is vital for monitoring and tracking crowd movement to enhance public security. However, re-identification in the presence of occlusion substantially reduces the performance of existing systems and is a challenging area. In this work, we propose a plausible solution to this problem by developing effective occlusion detection and reconstruction framework for RGB images/videos consisting of Deep Neural Networks. Specifically, a CNN-based occlusion detection model classifies individual input frames, followed by a Conv-LSTM and Autoencoder to reconstruct the occluded pixels corresponding to the occluded frames for sequential (video) and non-sequential (image) data, respectively. The quality of the reconstructed RGB frames is further refined and fine-tuned using a Conditional Generative Adversarial Network (cGAN). Our method is evaluated on four well-known public data sets of the domain, and the qualitative reconstruction results are indeed appealing. Quantitative evaluation in terms of re-identification accuracy of the Siamese network showed an exceptional Rank-1 accuracy after occluded pixel reconstruction on various datasets. A comparative analysis with state-of-the-art approaches also demonstrates the robustness of our work for use in real-life surveillance systems.

논문 ID: 3161.35482

DOMFN: A Divergence-Orientated Multi-Modal Fusion Network for Resume Assessment

In talent management, resume assessment aims to analyze the quality of a job seeker's resume, which can assist recruiters to discover suitable candidates and benefit job seekers improving resume quality in return. Recent machine learning based methods on large-scale public resume datasets have provided the opportunity for automatic assessment for reducing manual costs. However, most existing approaches are still content-dominated and ignore other valuable information. Inspired by practical resume evaluations that consider both the content and layout, we construct the multi-modalities from resumes but face a new challenge that sometimes the performance of multi-modal fusion is even worse than the best uni-modality. In this paper, we experimentally find that this phenomenon is due to the cross-modal divergence. Therefore, we need to consider when is it appropriate to perform multi-modal fusion? To address this problem, we design an instance-aware fusion method, i.e., Divergence-Orientated Multi-Modal Fusion Network (DOMFN), which can adaptively fuse the uni-modal predictions and multi-modal prediction based on cross-modal divergence. Specifically, DOMFN computes a functional penalty score to measure the divergence of cross-modal predictions. Then, the learned divergence can be used to decide whether to conduct multi-modal fusion and be adopted into an amended loss for reliable training. Consequently, DOMFN rejects multi-modal prediction when the cross-modal divergence is too large, avoiding the overall performance degradation, so as to achieve better performance than uni-modalities. In experiments, qualitative comparison with baselines on real-world dataset demonstrates the superiority and explainability of the proposed DOMFN, e.g., we find a meaningful phenomenon that multi-modal fusion has positive effects for assessing resumes from UI Designer and Enterprise Service positions, whereas affects the assessment of Technology and Product Operation positions.

arXiv:2304.06696

Improving novelty detection with generative adversarial networks on hand gesture data

We propose a novel way of solving the issue of classification of out-of-vocabulary gestures using Artificial Neural Networks (ANNs) trained in the Generative Adversarial Network (GAN) framework. A generative model augments the data set in an online fashion with new samples and stochastic target vectors, while a discriminative model determines the class of the samples. The approach was evaluated on the UC2017 SG and UC2018 DualMyo data sets. The generative models performance was measured with a distance metric between generated and real samples. The discriminative models were evaluated by their accuracy on trained and novel classes. In terms of sample generation quality, the GAN is significantly better than a random distribution (noise) in mean distance, for all classes. In the classification tests, the baseline neural network was not capable of identifying untrained gestures. When the proposed methodology was implemented, we found that there is a trade-off between the detection of trained and untrained gestures, with some trained samples being mistaken as novelty. Nevertheless, a novelty detection accuracy of 95.4% or 90.2% (depending on the data set) was achieved with just 5% loss of accuracy on trained classes.

arXiv:2304.06297

ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.

arXiv:2304.05556

An End-to-End Network for Upright Adjustment of Panoramic Images

Nowadays, panoramic images can be easily obtained by panoramic cameras. However, when the panoramic camera orientation is tilted, a non-upright panoramic image will be captured. Existing upright adjustment models focus on how to estimate more accurate camera orientation, and attribute image reconstruction to offline or post-processing tasks. To this end, we propose an online end-to-end network for upright adjustment. Our network is designed to reconstruct the image while finding the angle. Our network consists of three modules: orientation estimation, LUT online generation, and upright reconstruction. Direction estimation estimates the tilt angle of the panoramic image. Then, a converter block with upsampling function is designed to generate angle to LUT. This module can output corresponding online LUT for different input angles. Finally, a lightweight generative adversarial network (GAN) aims to generate upright images from shallow features. The experimental results show that in terms of angles, we have improved the accuracy of small angle errors. In terms of image reconstruction, In image reconstruction, we have achieved the first real-time online upright reconstruction of panoramic images using deep learning networks.

arXiv:2304.05498

GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery

Recent advances in deep learning have accelerated its use in various applications, such as cellular image analysis and molecular discovery. In molecular discovery, a generative adversarial network (GAN), which comprises a discriminator to distinguish generated molecules from existing molecules and a generator to generate new molecules, is one of the premier technologies due to its ability to learn from a large molecular data set efficiently and generate novel molecules that preserve similar properties. However, different pharmaceutical companies may be unwilling or unable to share their local data sets due to the geo-distributed and sensitive nature of molecular data sets, making it impossible to train GANs in a centralized manner. In this paper, we propose a Graph convolutional network in Generative Adversarial Networks via Federated learning (GraphGANFed) framework, which integrates graph convolutional neural Network (GCN), GAN, and federated learning (FL) as a whole system to generate novel molecules without sharing local data sets. In GraphGANFed, the discriminator is implemented as a GCN to better capture features from molecules represented as molecular graphs, and FL is used to train both the discriminator and generator in a distributive manner to preserve data privacy. Extensive simulations are conducted based on the three bench-mark data sets to demonstrate the feasibility and effectiveness of GraphGANFed. The molecules generated by GraphGANFed can achieve high novelty (=100) and diversity (> 0.9). The simulation results also indicate that 1) a lower complexity discriminator model can better avoid mode collapse for a smaller data set, 2) there is a tradeoff among different evaluation metrics, and 3) having the right dropout ratio of the generator and discriminator can avoid mode collapse.

arXiv:2304.04541

Sequential Recommendation with Diffusion Models

Generative models, such as Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN), have been successfully applied in sequential recommendation. These methods require sampling from probability distributions and adopt auxiliary loss functions to optimize the model, which can capture the uncertainty of user behaviors and alleviate exposure bias. However, existing generative models still suffer from the posterior collapse problem or the model collapse problem, thus limiting their applications in sequential recommendation. To tackle the challenges mentioned above, we leverage a new paradigm of the generative models, i.e., diffusion models, and present sequential recommendation with diffusion models (DiffRec), which can avoid the issues of VAE- and GAN-based models and show better performance. While diffusion models are originally proposed to process continuous image data, we design an additional transition in the forward process together with a transition in the reverse process to enable the processing of the discrete recommendation data. We also design a different noising strategy that only noises the target item instead of the whole sequence, which is more suitable for sequential recommendation. Based on the modified diffusion process, we derive the objective function of our framework using a simplification technique and design a denoise sequential recommender to fulfill the objective function. As the lengthened diffusion steps substantially increase the time complexity, we propose an efficient training strategy and an efficient inference strategy to reduce training and inference cost and improve recommendation diversity. Extensive experiment results on three public benchmark datasets verify the effectiveness of our approach and show that DiffRec outperforms the state-of-the-art sequential recommendation models.

arXiv:2304.04386

Generating Adversarial Attacks in the Latent Space

Adversarial attacks in the input (pixel) space typically incorporate noise margins such as $L_1$ or $L_{\infty}$-norm to produce imperceptibly perturbed data that confound deep learning networks. Such noise margins confine the magnitude of permissible noise. In this work, we propose injecting adversarial perturbations in the latent (feature) space using a generative adversarial network, removing the need for margin-based priors. Experiments on MNIST, CIFAR10, Fashion-MNIST, CIFAR100 and Stanford Dogs datasets support the effectiveness of the proposed method in generating adversarial attacks in the latent space while ensuring a high degree of visual realism with respect to pixel-based adversarial attack methods.

arXiv:2304.04291

ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis

Micropaleontology in geosciences focuses on studying the evolution of microfossils (e.g., foraminifera) through geological records to reconstruct past environmental and climatic conditions. This field heavily relies on visual recognition of microfossil features, making it suitable for computer vision technology, specifically deep convolutional neural networks (CNNs), to automate and optimize microfossil identification and classification. However, the application of deep learning in micropaleontology is hindered by limited availability of high-quality, high-resolution labeled fossil images and the significant manual labeling effort required by experts. To address these challenges, we propose a novel deep learning workflow combining hierarchical vision transformers with style-based generative adversarial network algorithms to efficiently acquire and synthetically generate realistic high-resolution labeled datasets of micropaleontology in large volumes. Our study shows that this workflow can generate high-resolution images with a high signal-to-noise ratio (39.1 dB) and realistic synthetic images with a Frechet inception distance similarity score of 14.88. Additionally, our workflow provides a large volume of self-labeled datasets for model benchmarking and various downstream visual tasks, including fossil classification and segmentation. For the first time, we performed few-shot semantic segmentation of different foraminifera chambers on both generated and synthetic images with high accuracy. This novel meta-learning approach is only possible with the availability of high-resolution, high-volume labeled datasets. Our deep learning-based workflow shows promise in advancing and optimizing micropaleontological research and other visual-dependent geological analyses.

arXiv:2304.02739

Bengali Fake Review Detection using Semi-supervised Generative Adversarial Networks

This paper investigates the potential of semi-supervised Generative Adversarial Networks (GANs) to fine-tune pretrained language models in order to classify Bengali fake reviews from real reviews with a few annotated data. With the rise of social media and e-commerce, the ability to detect fake or deceptive reviews is becoming increasingly important in order to protect consumers from being misled by false information. Any machine learning model will have trouble identifying a fake review, especially for a low resource language like Bengali. We have demonstrated that the proposed semi-supervised GAN-LM architecture (generative adversarial network on top of a pretrained language model) is a viable solution in classifying Bengali fake reviews as the experimental results suggest that even with only 1024 annotated samples, BanglaBERT with semi-supervised GAN (SSGAN) achieved an accuracy of 83.59% and a f1-score of 84.89% outperforming other pretrained language models - BanglaBERT generator, Bangla BERT Base and Bangla-Electra by almost 3%, 4% and 10% respectively in terms of accuracy. The experiments were conducted on a manually labeled food review dataset consisting of total 6014 real and fake reviews collected from various social media groups. Researchers that are experiencing difficulty recognizing not just fake reviews but other classification issues owing to a lack of labeled data may find a solution in our proposed methodology.

arXiv:2304.00648

Improving RF-DNA Fingerprinting Performance in an Indoor Multipath Environment Using Semi-Supervised Learning

The number of Internet of Things (IoT) deployments is expected to reach 75.4 billion by 2025. Roughly 70% of all IoT devices employ weak or no encryption; thus, putting them and their connected infrastructure at risk of attack by devices that are wrongly authenticated or not authenticated at all. A physical layer security approach -- known as Specific Emitter Identification (SEI) -- has been proposed and is being pursued as a viable IoT security mechanism. SEI is advantageous because it is a passive technique that exploits inherent and distinct features that are unintentionally added to the signal by the IoT Radio Frequency (RF) front-end. SEI's passive exploitation of unintentional signal features removes any need to modify the IoT device, which makes it ideal for existing and future IoT deployments. Despite the amount of SEI research conducted, some challenges must be addressed to make SEI a viable IoT security approach. One challenge is the extraction of SEI features from signals collected under multipath fading conditions. Multipath corrupts the inherent SEI features that are used to discriminate one IoT device from another; thus, degrading authentication performance and increasing the chance of attack. This work presents two semi-supervised Deep Learning (DL) equalization approaches and compares their performance with the current state of the art. The two approaches are the Conditional Generative Adversarial Network (CGAN) and Joint Convolutional Auto-Encoder and Convolutional Neural Network (JCAECNN). Both approaches learn the channel distribution to enable multipath correction while simultaneously preserving the SEI exploited features. CGAN and JCAECNN performance is assessed using a Rayleigh fading channel under degrading SNR, up to thirty-two IoT devices, and two publicly available signal sets. The JCAECNN improves SEI performance by 10% beyond that of the current state of the art.

arXiv:2304.00083공식 코드 · Papers with Code

A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inference

The growing popularity of Machine Learning (ML) has led to its deployment in various sensitive domains, which has resulted in significant research focused on ML security and privacy. However, in some applications, such as Augmented/Virtual Reality, integrity verification of the outsourced ML tasks is more critical--a facet that has not received much attention. Existing solutions, such as multi-party computation and proof-based systems, impose significant computation overhead, which makes them unfit for real-time applications. We propose Fides, a novel framework for real-time integrity validation of ML-as-a-Service (MLaaS) inference. Fides features a novel and efficient distillation technique--Greedy Distillation Transfer Learning--that dynamically distills and fine-tunes a space and compute-efficient verification model for verifying the corresponding service model while running inside a trusted execution environment. Fides features a client-side attack detection model that uses statistical analysis and divergence measurements to identify, with a high likelihood, if the service model is under attack. Fides also offers a re-classification functionality that predicts the original class whenever an attack is identified. We devised a generative adversarial network framework for training the attack detection and re-classification models. The evaluation shows that Fides achieves an accuracy of up to 98% for attack detection and 94% for re-classification.

arXiv:2304.00725

CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images

Positron emission tomography (PET) is the most sensitive molecular imaging modality routinely applied in our modern healthcare. High radioactivity caused by the injected tracer dose is a major concern in PET imaging and limits its clinical applications. However, reducing the dose leads to inadequate image quality for diagnostic practice. Motivated by the need to produce high quality images with minimum low-dose, Convolutional Neural Networks (CNNs) based methods have been developed for high quality PET synthesis from its low-dose counterparts. Previous CNNs-based studies usually directly map low-dose PET into features space without consideration of different dose reduction level. In this study, a novel approach named CG-3DSRGAN (Classification-Guided Generative Adversarial Network with Super Resolution Refinement) is presented. Specifically, a multi-tasking coarse generator, guided by a classification head, allows for a more comprehensive understanding of the noise-level features present in the low-dose data, resulting in improved image synthesis. Moreover, to recover spatial details of standard PET, an auxiliary super resolution network - Contextual-Net - is proposed as a second-stage training to narrow the gap between coarse prediction and standard PET. We compared our method to the state-of-the-art methods on whole-body PET with different dose reduction factors (DRFs). Experiments demonstrate our method can outperform others on all DRF.

arXiv:2304.00433

Ideal Observer Computation by Use of Markov-Chain Monte Carlo with Generative Adversarial Networks

Medical imaging systems are often evaluated and optimized via objective, or task-specific, measures of image quality (IQ) that quantify the performance of an observer on a specific clinically-relevant task. The performance of the Bayesian Ideal Observer (IO) sets an upper limit among all observers, numerical or human, and has been advocated for use as a figure-of-merit (FOM) for evaluating and optimizing medical imaging systems. However, the IO test statistic corresponds to the likelihood ratio that is intractable to compute in the majority of cases. A sampling-based method that employs Markov-Chain Monte Carlo (MCMC) techniques was previously proposed to estimate the IO performance. However, current applications of MCMC methods for IO approximation have been limited to a small number of situations where the considered distribution of to-be-imaged objects can be described by a relatively simple stochastic object model (SOM). As such, there remains an important need to extend the domain of applicability of MCMC methods to address a large variety of scenarios where IO-based assessments are needed but the associated SOMs have not been available. In this study, a novel MCMC method that employs a generative adversarial network (GAN)-based SOM, referred to as MCMC-GAN, is described and evaluated. The MCMC-GAN method was quantitatively validated by use of test-cases for which reference solutions were available. The results demonstrate that the MCMC-GAN method can extend the domain of applicability of MCMC methods for conducting IO analyses of medical imaging systems.