PyTorchKR Papers

최신 논문

총 7,990편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2402.02188

Diabetes detection using deep learning techniques with oversampling and feature augmentation

Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential. Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated. Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art. Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.

arXiv:2402.01542공식 코드 · Papers with Code

Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic Interpolation

In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to generate geodesic interpolations resembling protein folding transitions, thereby improving sampling efficiency without true transition state samples. This new data can be used to improve the accuracy of classifier-based methods. Alternatively, a regression-based learning scheme for CV models can be adopted by leveraging the interpolation progress parameter.

arXiv:2402.01424

A Data-Driven Analysis of Robust Automatic Piano Transcription

Algorithms for automatic piano transcription have improved dramatically in recent years due to new datasets and modeling techniques. Recent developments have focused primarily on adapting new neural network architectures, such as the Transformer and Perceiver, in order to yield more accurate systems. In this work, we study transcription systems from the perspective of their training data. By measuring their performance on out-of-distribution annotated piano data, we show how these models can severely overfit to acoustic properties of the training data. We create a new set of audio for the MAESTRO dataset, captured automatically in a professional studio recording environment via Yamaha Disklavier playback. Using various data augmentation techniques when training with the original and re-performed versions of the MAESTRO dataset, we achieve state-of-the-art note-onset accuracy of 88.4 F1-score on the MAPS dataset, without seeing any of its training data. We subsequently analyze these data augmentation techniques in a series of ablation studies to better understand their influence on the resulting models.

arXiv:2402.01071공식 코드 · Papers with Code

Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities

The potential harms of the under-representation of minorities in training data, particularly in multi-modal settings, is a well-recognized concern. While there has been extensive effort in detecting such under-representation, resolution has remained a challenge. With recent advancements in generative AI, large language models and foundation models have emerged as versatile tools across various domains. In this paper, we propose Chameleon, a system that efficiently utilizes these tools to augment a data set with a minimal addition of synthetically generated tuples, in order to enhance the coverage of the under-represented groups. Our system follows a rejection sampling approach to ensure the generated tuples have a high quality and follow the underlying distribution. In order to minimize the rejection chance of the generated tuples, we propose multiple strategies for providing a guide for the foundation model. Our experiment results, in addition to confirming the efficiency of our proposed algorithms, illustrate the effectiveness of our approach, as the unfairness of the model in a downstream task significantly dropped after data repair using Chameleon.

arXiv:2402.01054공식 코드 · Papers with Code

Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data

AI models present a wide range of applications in the field of medicine. However, achieving optimal performance requires access to extensive healthcare data, which is often not readily available. Furthermore, the imperative to preserve patient privacy restricts patient data sharing with third parties and even within institutes. Recently, generative AI models have been gaining traction for facilitating open-data sharing by proposing synthetic data as surrogates of real patient data. Despite the promise, some of these models are susceptible to patient data memorization, where models generate patient data copies instead of novel synthetic samples. Considering the importance of the problem, surprisingly it has received relatively little attention in the medical imaging community. To this end, we assess memorization in unconditional latent diffusion models. We train latent diffusion models on CT, MR, and X-ray datasets for synthetic data generation. We then detect the amount of training data memorized utilizing our novel self-supervised copy detection approach and further investigate various factors that can influence memorization. Our findings show a surprisingly high degree of patient data memorization across all datasets. Comparison with non-diffusion generative models, such as autoencoders and generative adversarial networks, indicates that while latent diffusion models are more susceptible to memorization, overall they outperform non-diffusion models in synthesis quality. Further analyses reveal that using augmentation strategies, small architecture, and increasing dataset can reduce memorization while over-training the models can enhance it. Collectively, our results emphasize the importance of carefully training generative models on private medical imaging datasets, and examining the synthetic data to ensure patient privacy before sharing it for medical research and applications.

arXiv:2402.00851

Data Augmentation Scheme for Raman Spectra with Highly Correlated Annotations

In biotechnology Raman Spectroscopy is rapidly gaining popularity as a process analytical technology (PAT) that measures cell densities, substrate- and product concentrations. As it records vibrational modes of molecules it provides that information non-invasively in a single spectrum. Typically, partial least squares (PLS) is the model of choice to infer information about variables of interest from the spectra. However, biological processes are known for their complexity where convolutional neural networks (CNN) present a powerful alternative. They can handle non-Gaussian noise and account for beam misalignment, pixel malfunctions or the presence of additional substances. However, they require a lot of data during model training, and they pick up non-linear dependencies in the process variables. In this work, we exploit the additive nature of spectra in order to generate additional data points from a given dataset that have statistically independent labels so that a network trained on such data exhibits low correlations between the model predictions. We show that training a CNN on these generated data points improves the performance on datasets where the annotations do not bear the same correlation as the dataset that was used for model training. This data augmentation technique enables us to reuse spectra as training data for new contexts that exhibit different correlations. The additional data allows for building a better and more robust model. This is of interest in scenarios where large amounts of historical data are available but are currently not used for model training. We demonstrate the capabilities of the proposed method using synthetic spectra of Ralstonia eutropha batch cultivations to monitor substrate, biomass and polyhydroxyalkanoate (PHA) biopolymer concentrations during of the experiments.

arXiv:2402.00807

Augmenting Offline Reinforcement Learning with State-only Interactions

Batch offline data have been shown considerably beneficial for reinforcement learning. Their benefit is further amplified by upsampling with generative models. In this paper, we consider a novel opportunity where interaction with environment is feasible, but only restricted to observations, i.e., \textit{no reward} feedback is available. This setting is broadly applicable, as simulators or even real cyber-physical systems are often accessible, while in contrast reward is often difficult or expensive to obtain. As a result, the learner must make good sense of the offline data to synthesize an efficient scheme of querying the transition of state. Our method first leverages online interactions to generate high-return trajectories via conditional diffusion models. They are then blended with the original offline trajectories through a stitching algorithm, and the resulting augmented data can be applied generically to downstream reinforcement learners. Superior empirical performance is demonstrated over state-of-the-art data augmentation methods that are extended to utilize state-only interactions.

arXiv:2402.00593

Coronary Artery Disease Classification with Different Lesion Degree Ranges based on Deep Learning

Invasive Coronary Angiography (ICA) images are considered the gold standard for assessing the state of the coronary arteries. Deep learning classification methods are widely used and well-developed in different areas where medical imaging evaluation has an essential impact due to the development of computer-aided diagnosis systems that can support physicians in their clinical procedures. In this paper, a new performance analysis of deep learning methods for binary ICA classification with different lesion degrees is reported. To reach this goal, an annotated dataset of ICA images that contains the ground truth, the location of lesions and seven possible severity degrees ranging between 0% and 100% was employed. The ICA images were divided into 'lesion' or 'non-lesion' patches. We aim to study how binary classification performance is affected by the different lesion degrees considered in the positive class. Therefore, five known convolutional neural network architectures were trained with different input images where different lesion degree ranges were gradually incorporated until considering the seven lesion degrees. Besides, four types of experiments with and without data augmentation were designed, whose F-measure and Area Under Curve (AUC) were computed. Reported results achieved an F-measure and AUC of 92.7% and 98.1%, respectively. However, lesion classification is highly affected by the degree of the lesion intended to classify, with 15% less accuracy when <99% lesion patches are present.

arXiv:2402.00541

Masked Conditional Diffusion Model for Enhancing Deepfake Detection

Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen during training. In this paper, deepfake data to help detect deepfakes. this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection. It generates a variety of forged faces from a masked pristine one, encouraging the deepfake detection model to learn generic and robust representations without overfitting to special artifacts. Extensive experiments demonstrate that forgery images generated with our method are of high quality and helpful to improve the performance of deepfake detection models.

arXiv:2402.00086

Retrosynthesis prediction enhanced by in-silico reaction data augmentation

Recent advances in machine learning (ML) have expedited retrosynthesis research by assisting chemists to design experiments more efficiently. However, all ML-based methods consume substantial amounts of paired training data (i.e., chemical reaction: product-reactant(s) pair), which is costly to obtain. Moreover, companies view reaction data as a valuable asset and restrict the accessibility to researchers. These issues prevent the creation of more powerful retrosynthesis models due to their data-driven nature. As a response, we exploit easy-to-access unpaired data (i.e., one component of product-reactant(s) pair) for generating in-silico paired data to facilitate model training. Specifically, we present RetroWISE, a self-boosting framework that employs a base model inferred from real paired data to perform in-silico reaction generation and augmentation using unpaired data, ultimately leading to a superior model. On three benchmark datasets, RetroWISE achieves the best overall performance against state-of-the-art models (e.g., +8.6% top-1 accuracy on the USPTO-50K test dataset). Moreover, it consistently improves the prediction accuracy of rare transformations. These results show that Retro- WISE overcomes the training bottleneck by in-silico reactions, thereby paving the way toward more effective ML-based retrosynthesis models.

arXiv:2401.17509

Anything in Any Scene: Photorealistic Video Object Insertion

Realistic video simulation has shown significant potential across diverse applications, from virtual reality to film production. This is particularly true for scenarios where capturing videos in real-world settings is either impractical or expensive. Existing approaches in video simulation often fail to accurately model the lighting environment, represent the object geometry, or achieve high levels of photorealism. In this paper, we propose Anything in Any Scene, a novel and generic framework for realistic video simulation that seamlessly inserts any object into an existing dynamic video with a strong emphasis on physical realism. Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism. We experimentally demonstrate that Anything in Any Scene framework produces simulated videos of great geometric realism, lighting realism, and photorealism. By significantly mitigating the challenges associated with video data generation, our framework offers an efficient and cost-effective solution for acquiring high-quality videos. Furthermore, its applications extend well beyond video data augmentation, showing promising potential in virtual reality, video editing, and various other video-centric applications. Please check our project website https://anythinginanyscene.github.io for access to our project code and more high-resolution video results.

arXiv:2401.17373

Arabic Tweet Act: A Weighted Ensemble Pre-Trained Transformer Model for Classifying Arabic Speech Acts on Twitter

Speech acts are a speakers actions when performing an utterance within a conversation, such as asking, recommending, greeting, or thanking someone, expressing a thought, or making a suggestion. Understanding speech acts helps interpret the intended meaning and actions behind a speakers or writers words. This paper proposes a Twitter dialectal Arabic speech act classification approach based on a transformer deep learning neural network. Twitter and social media, are becoming more and more integrated into daily life. As a result, they have evolved into a vital source of information that represents the views and attitudes of their users. We proposed a BERT based weighted ensemble learning approach to integrate the advantages of various BERT models in dialectal Arabic speech acts classification. We compared the proposed model against several variants of Arabic BERT models and sequence-based models. We developed a dialectal Arabic tweet act dataset by annotating a subset of a large existing Arabic sentiment analysis dataset (ASAD) based on six speech act categories. We also evaluated the models on a previously developed Arabic Tweet Act dataset (ArSAS). To overcome the class imbalance issue commonly observed in speech act problems, a transformer-based data augmentation model was implemented to generate an equal proportion of speech act categories. The results show that the best BERT model is araBERTv2-Twitter models with a macro-averaged F1 score and an accuracy of 0.73 and 0.84, respectively. The performance improved using a BERT-based ensemble method with a 0.74 and 0.85 averaged F1 score and accuracy on our dataset, respectively.

arXiv:2401.17802공식 코드 · Papers with Code

Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning

Contrastive representation learning is crucial in time series analysis as it alleviates the issue of data noise and incompleteness as well as sparsity of supervision signal. However, existing constrastive learning frameworks usually focus on intral-temporal features, which fails to fully exploit the intricate nature of time series data. To address this issue, we propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp to obtain optimized sub-sequences. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series to learn the underlying structure feature on the unlabeled time series. Meanwhile, we design a supervised task to learn more robust representations and facilitate the contrastive learning process. Finally, we jointly optimize the above two tasks. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task. Extensive experiments, in comparison with state-of-the-arts, well demonstrate the effectiveness of DE-TSMCL, where the maximum improvement can reach to 27.3%.

arXiv:2401.17196

Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion of adversarial examples generated by existing methods change only one word. This single-word perturbation vulnerability represents a significant weakness in classifiers, which malicious users can exploit to efficiently create a multitude of adversarial examples. This paper studies this problem and makes the following key contributions: (1) We introduce a novel metric \r{ho} to quantitatively assess a classifier's robustness against single-word perturbation. (2) We present the SP-Attack, designed to exploit the single-word perturbation vulnerability, achieving a higher attack success rate, better preserving sentence meaning, while reducing computation costs compared to state-of-the-art adversarial methods. (3) We propose SP-Defense, which aims to improve \r{ho} by applying data augmentation in learning. Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves \r{ho} by 14.6% and 13.9% and decreases the attack success rate of SP-Attack by 30.4% and 21.2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.

arXiv:2401.16712공식 코드 · Papers with Code

LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field Cameras

Leveraging rich information is crucial for dense prediction tasks. Light field (LF) cameras are instrumental in this regard, as they allow data to be sampled from various perspectives. This capability provides valuable spatial, depth, and angular information, enhancing scene-parsing tasks. However, we have identified two overlooked issues for the LF salient object detection (SOD) task. (1): Previous approaches predominantly employ a customized two-stream design to discover the spatial and depth features within light field images. The network struggles to learn the implicit angular information between different images due to a lack of intra-network data connectivity. (2): Little research has been directed towards the data augmentation strategy for LF SOD. Research on inter-network data connectivity is scant. In this study, we propose an efficient paradigm (LF Tracy) to address those issues. This comprises a single-pipeline encoder paired with a highly efficient information aggregation (IA) module (around 8M parameters) to establish an intra-network connection. Then, a simple yet effective data augmentation strategy called MixLD is designed to bridge the inter-network connections. Owing to this innovative paradigm, our model surpasses the existing state-of-the-art method through extensive experiments. Especially, LF Tracy demonstrates a 23% improvement over previous results on the latest large-scale PKU dataset. The source code is publicly available at: https://github.com/FeiBryantkit/LF-Tracy.

논문 ID: document/1005078

Deep Regularized Waveform Learning for Beam Prediction With Limited Samples in Non-Cooperative mmWave Systems

Millimeter wave (mmWave) systems need beam management to establish and maintain reliable links. This complex and time-consuming process seriously affects communication efficiency. Benefiting from data-driven technology in deep learning, the beam can be predicted from the waveform without coordination between transceivers. By passively listening enough waveforms that are transmitted from the base station (BS) to other receivers, the BS can predict which beam is suitable for transmitting in the downlink. However, training such a waveform learning neural network usually requires a large number of labeled training samples. This is a huge challenge, because it is difficult for the receiver to get the precise signal parameters from the transmitter in advance in the non-cooperative mmWave system. As a result, the limited samples may cause overfitting and seriously restrict the performance. Although the data augmentation technology can improve the performance under limited samples, existing data augmentation methods are mostly based on strong prior knowledge which cannot further exploit the potential characteristics of data in the real environment. This paper proposes a mixed regularization training method for training the beam prediction neural network under limited training samples. Specifically, data augmentation is implemented in the data pre-processing procedure with prior knowledge and then the signal splicing strategy is proposed in the training procedure. In order to mine the time correlation characteristics of signals, the cyclic time shift (CTS) based data augmentation method is proposed in the data augmentation step. The simulation results show that our proposed deep regularized waveform learning method needs less training samples under the same performance. Moreover, the proposed method can achieve best performance compared with existing data augmentation methods.

arXiv:2401.17129공식 코드 · Papers with Code

Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes

This technical report details our work towards building an enhanced audio-visual sound event localization and detection (SELD) network. We build on top of the audio-only SELDnet23 model and adapt it to be audio-visual by merging both audio and video information prior to the gated recurrent unit (GRU) of the audio-only network. Our model leverages YOLO and DETIC object detectors. We also build a framework that implements audio-visual data augmentation and audio-visual synthetic data generation. We deliver an audio-visual SELDnet system that outperforms the existing audio-visual SELD baseline.

arXiv:2401.17086

Active Generation Network of Human Skeleton for Action Recognition

Data generation is a data augmentation technique for enhancing the generalization ability for skeleton-based human action recognition. Most existing data generation methods face challenges to ensure the temporal consistency of the dynamic information for action. In addition, the data generated by these methods lack diversity when only a few training samples are available. To solve those problems, We propose a novel active generative network (AGN), which can adaptively learn various action categories by motion style transfer to generate new actions when the data for a particular action is only a single sample or few samples. The AGN consists of an action generation network and an uncertainty metric network. The former, with ST-GCN as the Backbone, can implicitly learn the morphological features of the target action while preserving the category features of the source action. The latter guides generating actions. Specifically, an action recognition model generates prediction vectors for each action, which is then scored using an uncertainty metric. Finally, UMN provides the uncertainty sampling basis for the generated actions.

arXiv:2401.16453

Hybrid Transformer and Spatial-Temporal Self-Supervised Learning for Long-term Traffic Prediction

Long-term traffic prediction has always been a challenging task due to its dynamic temporal dependencies and complex spatial dependencies. In this paper, we propose a model that combines hybrid Transformer and spatio-temporal self-supervised learning. The model enhances its robustness by applying adaptive data augmentation techniques at the sequence-level and graph-level of the traffic data. It utilizes Transformer to overcome the limitations of recurrent neural networks in capturing long-term sequences, and employs Chebyshev polynomial graph convolution to capture complex spatial dependencies. Furthermore, considering the impact of spatio-temporal heterogeneity on traffic speed, we design two self-supervised learning tasks to model the temporal and spatial heterogeneity, thereby improving the accuracy and generalization ability of the model. Experimental evaluations are conducted on two real-world datasets, PeMS04 and PeMS08, and the results are visualized and analyzed, demonstrating the superior performance of the proposed model.

arXiv:2401.16349

ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning

A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes, and helps a job seeker find relevant jobs from a list of job posts. However, since job seekers apply only to a few jobs, interaction records in resume-job datasets are sparse. Different from many prior work that use complex modeling techniques, we tackle this sparsity problem using data augmentations and a simple contrastive learning approach. ConFit first creates an augmented resume-job dataset by paraphrasing specific sections in a resume or a job post. Then, ConFit uses contrastive learning to further increase training samples from $B$ pairs per batch to $O(B^2)$ per batch. We evaluate ConFit on two real-world datasets and find it outperforms prior methods (including BM25 and OpenAI text-ada-002) by up to 19% and 31% absolute in nDCG@10 for ranking jobs and ranking resumes, respectively.