arXiv subjects

Seong-Whan Lee

Publications and source records attributed to Seong-Whan Lee.

At least 145 records · Page 8Linked to original sources

arXiv2021

Interpretable Convolutional Neural Networks for Subject-Independent Motor Imagery Classification

Deep learning frameworks have become increasingly popular in brain computer interface (BCI) study thanks to their outstanding performance. However, in terms of the classification model alone, they are treated as black box as they do not provide any information on what led them to reach a particular decision. In other words, we cannot convince whether the high performance was aroused by the neuro-physiological factors or simply noise. Because of this disadvantage, it is difficult to ensure adequate reliability compared to their high performance. In this study, we propose an explainable deep learning model for BCI. Specifically, we aim to classify EEG signal which is obtained from the motor-imagery (MI) task. In addition, we adopted layer-wise relevance propagation (LRP) to the model to interpret the reason that the model derived certain classification output. We visualized the heatmap which indicates the output of the LRP in form of topography to certify neuro-physiological factors. Furthermore, we classified EEG with the subject-independent manner to learn robust and generalized EEG features by avoiding subject dependency. The methodology also provides the advantage of avoiding the expense of building training data for each subject. With our proposed model, we obtained generalized heatmap patterns for all subjects. As a result, we can conclude that our proposed model provides neuro-physiologically reliable interpretation.

cs.NE↗

arXiv2021

Mobile BCI dataset of scalp- and ear-EEGs with ERP and SSVEP paradigms while standing, walking, and running

We present a mobile dataset obtained from electroencephalography (EEG) of the scalp and around the ear as well as from locomotion sensors by 24 participants moving at four different speeds while performing two brain-computer interface (BCI) tasks. The data were collected from 32-channel scalp-EEG, 14-channel ear-EEG, 4-channel electrooculography, and 9-channel inertial measurement units placed at the forehead, left ankle, and right ankle. The recording conditions were as follows: standing, slow walking, fast walking, and slight running at speeds of 0, 0.8, 1.6, and 2.0m/s, respectively. For each speed, two different BCI paradigms, event-related potential and steady-state visual evoked potential, were recorded. To evaluate the signal quality, scalp- and ear-EEG data were qualitatively and quantitatively validated during each speed. We believe that the dataset will facilitate BCIs in diverse mobile environments to analyze brain activities and evaluate the performance quantitatively for expanding the use of practical BCIs.

cs.HC↗

arXiv2021

Counterfactual Explanation Based on Gradual Construction for Deep Networks

To understand the black-box characteristics of deep networks, counterfactual explanation that deduces not only the important features of an input space but also how those features should be modified to classify input as a target class has gained an increasing interest. The patterns that deep networks have learned from a training dataset can be grasped by observing the feature variation among various classes. However, current approaches perform the feature modification to increase the classification probability for the target class irrespective of the internal characteristics of deep networks. This often leads to unclear explanations that deviate from real-world data distributions. To address this problem, we propose a counterfactual explanation method that exploits the statistics learned from a training dataset. Especially, we gradually construct an explanation by iterating over masking and composition steps. The masking step aims to select an important feature from the input data to be classified as a target class. Meanwhile, the composition step aims to optimize the previously selected feature by ensuring that its output score is close to the logit space of the training data that are classified as the target class. Experimental results show that our method produces human-friendly interpretations on various classification datasets and verify that such interpretations can be achieved with fewer feature modification.

cs.LG↗

arXiv2021

Subject-Independent Brain-Computer Interface for Decoding High-Level Visual Imagery Tasks

Brain-computer interface (BCI) is used for communication between humans and devices by recognizing status and intention of humans. Communication between humans and a drone using electroencephalogram (EEG) signals is one of the most challenging issues in the BCI domain. In particular, the control of drone swarms (the direction and formation) has more advantages compared to the control of a drone. The visual imagery (VI) paradigm is that subjects visually imagine specific objects or scenes. Reduction of the variability among EEG signals of subjects is essential for practical BCI-based systems. In this study, we proposed the subepoch-wise feature encoder (SEFE) to improve the performances in the subject-independent tasks by using the VI dataset. This study is the first attempt to demonstrate the possibility of generalization among subjects in the VI-based BCI. We used the leave-one-subject-out cross-validation for evaluating the performances. We obtained higher performances when including our proposed module than excluding our proposed module. The DeepConvNet with SEFE showed the highest performance of 0.72 among six different decoding models. Hence, we demonstrated the feasibility of decoding the VI dataset in the subject-independent task with robust performances by using our proposed module.

cs.CV↗

arXiv2021

GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints

Few-shot speaker adaptation is a specific Text-to-Speech (TTS) system that aims to reproduce a novel speaker's voice with a few training data. While numerous attempts have been made to the few-shot speaker adaptation system, there is still a gap in terms of speaker similarity to the target speaker depending on the amount of data. To bridge the gap, we propose GC-TTS which achieves high-quality speaker adaptation with significantly improved speaker similarity. Specifically, we leverage two geometric constraints to learn discriminative speaker representations. Here, a TTS model is pre-trained for base speakers with a sufficient amount of data, and then fine-tuned for novel speakers on a few minutes of data with two geometric constraints. Two geometric constraints enable the model to extract discriminative speaker embeddings from limited data, which leads to the synthesis of intelligible speech. We discuss and verify the effectiveness of GC-TTS by comparing it with popular and essential methods. The experimental results demonstrate that GC-TTS generates high-quality speech from only a few minutes of training data, outperforming standard techniques in terms of speaker similarity to the target speaker.

eess.AS↗

arXiv2021

Learning Free-Form Deformation for 3D Face Reconstruction from In-The-Wild Images

The 3D Morphable Model (3DMM), which is a Principal Component Analysis (PCA) based statistical model that represents a 3D face using linear basis functions, has shown promising results for reconstructing 3D faces from single-view in-the-wild images. However, 3DMM has restricted representation power due to the limited number of 3D scans and the global linear basis. To address the limitations of 3DMM, we propose a straightforward learning-based method that reconstructs a 3D face mesh through Free-Form Deformation (FFD) for the first time. FFD is a geometric modeling method that embeds a reference mesh within a parallelepiped grid and deforms the mesh by moving the sparse control points of the grid. As FFD is based on mathematically defined basis functions, it has no limitation in representation power. Thus, we can recover accurate 3D face meshes by estimating appropriate deviation of control points as deformation parameters. Although both 3DMM and FFD are parametric models, it is difficult to predict the effect of the 3DMM parameters on the face shape, while the deformation parameters of FFD are interpretable in terms of their effect on the final shape of the mesh. This practical advantage of FFD allows the resulting mesh and control points to serve as a good starting point for 3D face modeling, in that ordinary users can fine-tune the mesh by using widely available 3D software tools. Experiments on multiple datasets demonstrate how our method successfully estimates the 3D face geometry and facial expressions from 2D face images, achieving comparable performance to the state-of-the-art methods.

cs.CV↗

arXiv2021

Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Units

As interpretability has been pointed out as the obstacle to the adoption of Deep Neural Networks (DNNs), there is an increasing interest in solving a transparency issue to guarantee the impressive performance. In this paper, we demonstrate the efficiency of recent attribution techniques to explain the diagnostic decision by visualizing the significant factors in the input image. By utilizing the characteristics of objectness that DNNs have learned, fully decomposing the network prediction visualizes clear localization of target lesion. To verify our work, we conduct our experiments on Chest X-ray diagnosis with publicly accessible datasets. As an intuitive assessment metric for explanations, we report the performance of intersection of Union between visual explanation and bounding box of lesions. Experiment results show that recently proposed attribution methods visualize the more accurate localization for the diagnostic decision compared to the traditionally used CAM. Furthermore, we analyze the inconsistency of intentions between humans and DNNs, which is easily obscured by high performance. By visualizing the relevant factors, it is possible to confirm that the criterion for decision is in line with the learning strategy. Our analysis of unmasking machine intelligence represents the necessity of explainability in the medical diagnostic decision.

eess.IV↗

arXiv2021

Precise Aerial Image Matching based on Deep Homography Estimation

Aerial image registration or matching is a geometric process of aligning two aerial images captured in different environments. Estimating the precise transformation parameters is hindered by various environments such as time, weather, and viewpoints. The characteristics of the aerial images are mainly composed of a straight line owing to building and road. Therefore, the straight lines are distorted when estimating homography parameters directly between two images. In this paper, we propose a deep homography alignment network to precisely match two aerial images by progressively estimating the various transformation parameters. The proposed network is possible to train the matching network with a higher degree of freedom by progressively analyzing the transformation parameters. The precision matching performances have been increased by applying homography transformation. In addition, we introduce a method that can effectively learn the difficult-to-learn homography estimation network. Since there is no published learning data for aerial image registration, in this paper, a pair of images to which random homography transformation is applied within a certain range is used for learning. Hence, we could confirm that the deep homography alignment network shows high precision matching performance compared with conventional works.

cs.CV↗

arXiv2021

Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation

Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities. However, current deep learning solutions for dermatological lesion analysis are typically limited in providing probabilistic predictions which highlights the importance of concerning uncertainties. This concept of uncertainty can provide a confidence level for each feature which prevents overconfident predictions with poor generalization on unseen data. In this paper, we propose an overall framework that jointly considers dermatological classification and uncertainty estimation together. The estimated confidence of each feature to avoid uncertain feature and undesirable shift, which are caused by environmental difference of input image, in the latent space is pooled from confidence network. Our qualitative results show that modeling uncertainties not only helps to quantify model confidence for each prediction but also helps classification layers to focus on confident features, therefore, improving the accuracy for dermatological lesion classification. We demonstrate the potential of the proposed approach in two state-of-the-art dermoscopic datasets (ISIC 2018 and ISIC 2019).

cs.CV↗

arXiv2021

Motor Imagery Classification based on CNN-GRU Network with Spatio-Temporal Feature Representation

Recently, various deep neural networks have been applied to classify electroencephalogram (EEG) signal. EEG is a brain signal that can be acquired in a non-invasive way and has a high temporal resolution. It can be used to decode the intention of users. As the EEG signal has a high dimension of feature space, appropriate feature extraction methods are needed to improve classification performance. In this study, we obtained spatio-temporal feature representation and classified them with the combined convolutional neural networks (CNN)-gated recurrent unit (GRU) model. To this end, we obtained covariance matrices in each different temporal band and then concatenated them on the temporal axis to obtain a final spatio-temporal feature representation. In the classification model, CNN is responsible for spatial feature extraction and GRU is responsible for temporal feature extraction. Classification performance was improved by distinguishing spatial data processing and temporal data processing. The average accuracy of the proposed model was 77.70% for the BCI competition IV_2a data set. The proposed method outperformed all other methods compared as a baseline method.

cs.NE↗

arXiv2021

DAL: Feature Learning from Overt Speech to Decode Imagined Speech-based EEG Signals with Convolutional Autoencoder

Brain-computer interface (BCI) is one of the tools which enables the communication between humans and devices by reflecting intention and status of humans. With the development of artificial intelligence, the interest in communication between humans and drones using electroencephalogram (EEG) is increased. Especially, in the case of controlling drone swarms such as direction or formation, there are many advantages compared with controlling a drone unit. Imagined speech is one of the endogenous BCI paradigms, which can identify intentions of users. When conducting imagined speech, the users imagine the pronunciation as if actually speaking. In contrast, overt speech is a task in which the users directly pronounce the words. When controlling drone swarms using imagined speech, complex commands can be delivered more intuitively, but decoding performance is lower than that of other endogenous BCI paradigms. We proposed the Deep-autoleaner (DAL) to learn EEG features of overt speech for imagined speech-based EEG signals classification. To the best of our knowledge, this study is the first attempt to use EEG features of overt speech to decode imagined speech-based EEG signals with an autoencoder. A total of eight subjects participated in the experiment. When classifying four words, the average accuracy of the DAL was 48.41%. In addition, when comparing the performance between w/o and w/ EEG features of overt speech, there was a performance improvement of 7.42% when including EEG features of overt speech. Hence, we demonstrated that EEG features of overt speech could improve the decoding performance of imagined speech.

eess.SP↗

arXiv2021

One-Class Classification for Wafer Map using Adversarial Autoencoder with DSVDD Prior

Recently, semiconductors' demand has exploded in virtual reality, smartphones, wearable devices, the internet of things, robotics, and automobiles. Semiconductor manufacturers want to make semiconductors with high yields. To do this, manufacturers conduct many quality assurance activities. Wafer map pattern classification is a typical way of quality assurance. The defect pattern on the wafer map can tell us which process has a problem. Most of the existing wafer map classification methods are based on supervised methods. The supervised methods tend to have high performance, but they require extensive labor and expert knowledge to produce labeled datasets with a balanced distribution in mind. In the semiconductor manufacturing process, it is challenging to get defect data with balanced distribution. In this paper, we propose a one-class classification method using an Adversarial Autoencoder (AAE) with Deep Support Vector Data Description (DSVDD) prior, which generates random vectors within the hypersphere of DSVDD. We use the WM-811k dataset, which consists of a real-world wafer map. We compare the F1 score performance of our model with DSVDD and AAE.

cs.LG↗

arXiv2021

Detection of Abnormal Behavior with Self-Supervised Gaze Estimation

Due to the recent outbreak of COVID-19, many classes, exams, and meetings have been conducted non-face-to-face. However, the foundation for video conferencing solutions is still insufficient. So this technology has become an important issue. In particular, these technologies are essential for non-face-to-face testing, and technology dissemination is urgent. In this paper, we present a single video conferencing solution using gaze estimation in preparation for these problems. Gaze is an important cue for the tasks such as analysis of human behavior. Hence, numerous studies have been proposed to solve gaze estimation using deep learning, which is one of the most prominent methods up to date. We use these gaze estimation methods to detect abnormal behavior of video conferencing participants. Our contribution is as follows. i) We find and apply the optimal network for the gaze estimation method and apply a self-supervised method to improve accuracy. ii) For anomaly detection, we present a new dataset that aggregates the values of a new gaze, head pose, etc. iii) We train newly created data on Multi Layer Perceptron (MLP) models to detect anomaly behavior based on deep learning. We demonstrate the robustness of our method through experiments.

cs.CV↗

arXiv2021

Domain Generalization with Pseudo-Domain Label for Face Anti-Spoofing

Face anti-spoofing (FAS) plays an important role in protecting face recognition systems from face representation attacks. Many recent studies in FAS have approached this problem with domain generalization technique. Domain generalization aims to increase generalization performance to better detect various types of attacks and unseen attacks. However, previous studies in this area have defined each domain simply as an anti-spoofing datasets and focused on developing learning techniques. In this paper, we proposed a method that enables network to judge its domain by itself with the clustered convolutional feature statistics from intermediate layers of the network, without labeling domains as datasets. We obtained pseudo-domain labels by not only using the network extracting features, but also using depth estimators, which were previously used only as an auxiliary task in FAS. In our experiments, we trained with three datasets and evaluated the performance with the remaining one dataset to demonstrate the effectiveness of the proposed method by conducting a total of four sets of experiments.

cs.CV↗

arXiv2021

Towards Natural Brain-Machine Interaction using Endogenous Potentials based on Deep Neural Networks

Human-robot collaboration has the potential to maximize the efficiency of the operation of autonomous robots. Brain-machine interface (BMI) would be a desirable technology to collaborate with robots since the intention or state of users can be translated from the neural activities. However, the electroencephalogram (EEG), which is one of the most popularly used non-invasive BMI modalities, has low accuracy and a limited degree of freedom (DoF) due to a low signal-to-noise ratio. Thus, improving the performance of multi-class EEG classification is crucial to develop more flexible BMI-based human-robot collaboration. In this study, we investigated the possibility for inter-paradigm classification of multiple endogenous BMI paradigms, such as motor imagery (MI), visual imagery (VI), and speech imagery (SI), to enhance the limited DoF while maintaining robust accuracy. We conducted the statistical and neurophysiological analyses on MI, VI, and SI and classified three paradigms using the proposed temporal information-based neural network (TINN). We confirmed that statistically significant features could be extracted on different brain regions when classifying three endogenous paradigms. Moreover, our proposed TINN showed the highest accuracy of 0.93 compared to the previous methods for classifying three different types of mental imagery tasks (MI, VI, and SI).

cs.HC↗

arXiv2021

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space. This difference leads to spectral artifacts such as hissing noise or reverberation, and thus degrades the sample quality. In this paper, we propose Fre-GAN which achieves frequency-consistent audio synthesis with highly improved generation quality. Specifically, we first present resolution-connected generator and resolution-wise discriminators, which help learn various scales of spectral distributions over multiple frequency bands. Additionally, to reproduce high-frequency components accurately, we leverage discrete wavelet transform in the discriminators. From our experiments, Fre-GAN achieves high-fidelity waveform generation with a gap of only 0.03 MOS compared to ground-truth audio while outperforming standard models in quality.

eess.AS↗

arXiv2021

Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets.

cs.CV↗

arXiv2021

Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech

Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of phoneme-to-frame sequences. As the complexity increases and efficiency decreases with every additional step, there is expanding demand in modern synthesis pipelines for end-to-end TTS with efficient internal aligners. In this work, we propose an end-to-end text-to-waveform network with a novel reinforcement learning based duration search method. Our proposed generator is feed-forward and the aligner trains the agent to make optimal duration predictions by receiving active feedback from actions taken to maximize cumulative reward. We demonstrate accurate alignments of phoneme-to-frame sequence generated from trained agents enhance fidelity and naturalness of synthesized audio. Experimental results also show the superiority of our proposed model compared to other state-of-the-art TTS models with internal and external aligners.

eess.AS↗