Search Results for author:
Found 149 papers, 61 papers with code
DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
Developing effective visual inspection models remains challenging due to the scarcity of defect data.
EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
We propose EdiText, a controllable text editing method that modify the reference text to desired attributes at various scales.
CNN-based TEM image denoising from first principles
Transmission electron microscope (TEM) images are often corrupted by noise, hindering their interpretation.
Know "No'' Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
While CLIP has significantly advanced multimodal understanding by bridging vision and language, the inability to grasp negation - such as failing to differentiate concepts like "parking" from "no parking" - poses substantial challenges.
Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation
Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling.
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks.
Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation
Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction.
Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision.
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
In this paper, we introduce Diptych Prompting, a novel zero-shot approach that reinterprets as an inpainting task with precise subject alignment by leveraging the emergent property of diptych generation in large-scale text-to-image models.
Style-Friendly SNR Sampler for Style-Driven Generation
Recent large-scale diffusion models generate high-quality images but struggle to learn new, personalized artistic styles, which limits the creation of unique style templates.
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
To address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs.
Interpretable Language Modeling via Induction-head Ngram Models
It again provides a significant improvement over interpretable models (20% relative increase in the correlation of predicted fMRI responses), potentially enabling deeper scientific investigation of language selectivity in the brain.
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure.
A Comprehensive Survey of Time Series Forecasting: Architectural Diversity and Open Challenges
By comparing and re-examining various deep learning models, we uncover new perspectives and presents the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models.
Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language.
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
LLMs often struggle to filter out irrelevant documents within the context, and their performance is sensitive to the position of supporting documents within that context.
Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models.
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
Through analysis and experiments on various versions of SD, we demonstrate that our proposed approach effectively reduces bias without additional training, achieving both efficiency and preservation of core image generation functionality.
CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detection
Although the identified Anomaly Cluster issue presents a significant challenge to applying k-nearest neighbor in UVAD, our proposed cleansing scheme effectively addresses this problem.
Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Based on our observations and the rationale about attention-based model dynamics, we propose a negative attention score (NAS) to systematically and quantitatively formulate negative bias.
Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models
To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model.
Disentangled Motion Modeling for Video Frame Interpolation
In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling.
Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context.
Self-Supervised Time-Series Anomaly Detection Using Learnable Data Augmentation
Continuous efforts are being made to advance anomaly detection in various manufacturing processes to increase the productivity and safety of industrial sites.
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach
In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task.
SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space.
Ranked #1 on
Domain Adaptation
on DomainNet
Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme.
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error.
Ranked #1 on
Test-time Adaptation
on ImageNet-C
Improving Diffusion-Based Generative Models via Approximated Optimal Transport
Our approach aims to approximate and integrate optimal transport into the training process, significantly enhancing the ability of diffusion models to estimate the denoiser outputs accurately.
Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models
Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input document.
GrounDial: Human-norm Grounded Safe Dialog Response Generation
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content.
Gradient Alignment with Prototype Feature for Fully Test-time Adaptation
In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label.
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
To construct USDM, we fine-tune our speech-text model on spoken dialog data using a multi-step spoken dialog template that stimulates the chain-of-reasoning capabilities exhibited by the underlying LLM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
DAFA: Distance-Aware Fair Adversarial Training
The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem.
On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss
Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models.
ControlDreamer: Blending Geometry and Style in Text-to-3D
Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation.
On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Model
An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models.
Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor
To facilitate this process, ScoPE employs a training objective that maximizes a target score, thoroughly considering both the ability to guide the text and its fluency.
PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
Blind-spot networks (BSNs) have been a prevalent choice to ensure J-invariance in self-supervised image denoising.
P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis.
1.5 million materials narratives generated by chatbots
The advent of artificial intelligence (AI) has enabled a comprehensive exploration of materials for various applications.
Mass Spectra Prediction with Structural Motif-based Graph Neural Networks
Mass spectra, which are agglomerations of ionized fragments from targeted molecules, play a crucial role across various fields for the identification of molecular structures.
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks.
Ranked #2 on
Visual Prompt Tuning
on VTAB-1k(Natural<7>)
Probabilistic Concept Bottleneck Models
To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM).
Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection
Diffusion-Stego achieved a high capacity of messages (3. 0 bpp of binary messages with 98% accuracy, and 6. 0 bpp with 90% accuracy) as well as high quality (with a FID score of 2. 77 for 1. 0 bpp on the FFHQ 64$\times$64 dataset) that makes it challenging to distinguish from real images in the PNG format.
Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models
Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts.
On the Impact of Knowledge Distillation for Model Interpretability
Several recent studies have elucidated why knowledge distillation (KD) improves model performance.
Sample-efficient Adversarial Imitation Learning
In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions.
Edit-A-Video: Single Video Editing with Object-Aware Consistency
Despite the fact that text-to-video (TTV) model has recently achieved remarkable success, there have been few approaches on TTV for its extension to video editing.
New Insights for the Stability-Plasticity Dilemma in Online Continual Learning
The aim of continual learning is to learn new tasks continuously (i. e., plasticity) without forgetting previously learned knowledge from old tasks (i. e., stability).
FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks
While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient.
E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
In terms of image quality, the LPIPS score improves by up to 12% and the reconstruction speed is 87% higher than that of ET-Net.
Confidence Score for Source-Free Unsupervised Domain Adaptation
Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge.
Out of Sight, Out of Mind: A Source-View-Wise Feature Aggregation for Multi-View Image-Based Rendering
Finally, for each element in the feature set, the aggregation features are extracted by calculating the weighted means and variances, where the weights are derived from the similarity distributions.
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments.
Ranked #2 on
Speech Synthesis
on LibriTTS
(using extra training data)
Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds.
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack.
Perception Prioritized Training of Diffusion Models
Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i. e., denoising score matching loss.
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels.
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
To take such non-linear characteristics into account, we introduce Label-Gradient Alignment (LGA), a novel NTK-based metric whose inherent formulation allows it to capture the large amount of non-linear advantage present in modern neural architectures.
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (e. g. train and rail), fundamentally bounding the performance of WSSS.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Dataset Condensation with Contrastive Signals
However, in this study, we prove that the existing DC methods can perform worse than the random selection method when task-irrelevant information forms a significant part of the training dataset.
AutoSNN: Towards Energy-Efficient Spiking Neural Networks
We investigate the design choices used in the previous studies in terms of the accuracy and number of spikes and figure out that they are not best-suited for SNNs.
BNUDC: A Two-Branched Deep Neural Network for Restoring Images From Under-Display Cameras
The images captured by under-display cameras (UDCs) are degraded by the screen in front of them.
Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
The computer-aided diagnosis of focal liver lesions (FLLs) can help improve workflow and enable correct diagnoses; FLL detection is the first step in such a computer-aided diagnosis.
Automatic Liver And Tumor Segmentation
Computed Tomography (CT)
+4
Supervised Neural Discrete Universal Denoiser for Adaptive Denoising
Namely, we make the supervised pre-training of Neural DUDE compatible with the adaptive fine-tuning of the parameters based on the given noisy data subject to denoising.
Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance
For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset.
Scalable Smartphone Cluster for Deep Learning
We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library.
Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object.
Ranked #20 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
FICGAN: Facial Identity Controllable GAN for De-identification
In this work, we present Facial Identity Controllable GAN (FICGAN) for not only generating high-quality de-identified face images with ensured privacy protection, but also detailed controllability on attribute preservation for enhanced data utility.
Guided-TTS:Text-to-Speech with Untranscribed Speech
By modeling the unconditional distribution for speech, our model can utilize the untranscribed data for training.
Confidence Score Weighting Adaptation for Source-Free Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to achieve high performance within the unlabeled target domain by leveraging the labeled source domain.
Biased Multi-Domain Adversarial Training
Several recent studies have shown that the use of extra in-distribution data can lead to a high level of adversarial robustness.
Variational Perturbations for Visual Feature Attribution
Explaining a complex black-box system in a post-hoc manner is important to understand its predictions.
AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition.
Towards a Rigorous Evaluation of Time-series Anomaly Detection
Furthermore, we question the potential of existing TAD methods by showing that an untrained model obtains comparable detection performance to the existing methods even when PA is forbidden.
Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings
AGG addresses the degeneration problem by gating the specific part of the gradient for rare token embeddings.
ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image.
Toward Spatially Unbiased Generative Models
From our observations, the generator's implicit positional encoding is translation-variant, making the generator spatially biased.
AdvRush: Searching for Adversarially Robust Neural Architectures
Current efforts to improve the robustness of neural networks against adversarial examples are focused on developing robust training methods, which update the weights of a neural network in a more robust direction.
TargetNet: Functional microRNA Target Prediction with Deep Neural Networks
Results: In this paper, we introduce TargetNet, a novel deep learning-based algorithm for functional miRNA target prediction.
GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks.
Energy-efficient Knowledge Distillation for Spiking Neural Networks
On MNIST dataset, our proposed student SNN achieves up to 0. 09% higher accuracy and produces 65% less spikes compared to the student SNN trained with conventional knowledge distillation method.
Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
Message passing neural network provides an effective framework for capturing molecular geometric features with the perspective of a molecule as a graph.
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
Accelerating Neural Architecture Search via Proxy Data
By analyzing proxy data constructed using various selection methods through data entropy, we propose a novel proxy data selection method tailored for NAS.
Stein Latent Optimization for Generative Adversarial Networks
Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner.
Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding
With TTFS coding, each neuron generates one spike at most, which leads to a significant improvement in energy efficiency.
Noise-Robust Deep Spiking Neural Networks with Temporal Information
Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information.
XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations
Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases.
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object.
BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation
Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object.
Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Herein, we propose a data augmentation method to improve generalization in both adversarial and standard learning by using out-of-distribution (OOD) data that are devoid of the abovementioned issues.
Variational saliency maps for explaining model's behavior
Saliency maps have been widely used to explain the behavior of an image classifier.
Interpretation of NLP models through input marginalization
To demystify the "black box" property of deep neural networks for natural language processing (NLP), several methods have been proposed to interpret their predictions by measuring the change in prediction probability after erasing each token of an input.
Information-Theoretic Visual Explanation for Black-Box Classifiers
IG map provides a class-independent answer to "How informative is each pixel?
iCaps: An Interpretable Classifier via Disentangled Capsule Networks
We propose an interpretable Capsule Network, iCaps, for image classification.
Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation
In this paper, we address the problem of image anomaly detection and segmentation.
Ranked #12 on
Anomaly Detection
on BTAD
(Segmentation AUROC metric, using extra
training data)
Joint Contrastive Learning for Unsupervised Domain Adaptation
Enhancing feature transferability by matching marginal distributions has led to improvements in domain adaptation, although this is at the expense of feature discrimination.
NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis.
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
By leveraging the properties of flows, MAS searches for the most probable monotonic alignment between text and the latent representation of speech.
Ranked #4 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding
Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems.
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization
In this paper, we identify Adversarial Feature Overfitting (AFO), which may cause poor adversarially robust generalization, and we show that adversarial training can overshoot the optimal point in terms of robust generalization, leading to AFO in our simple Gaussian model.
Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information
Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling.
Ranked #17 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image.
One-Shot Learning for Text-to-SQL Generation
We show that our model outperforms state-of-the-art approaches for various text-to-SQL datasets in two aspects: 1) the SQL generation accuracy for the trained templates, and 2) the adaptability to the unseen SQL templates based on a single example without any additional training.
Learning Condensed and Aligned Features for Unsupervised Domain Adaptation Using Label Propagation
We propose a novel domain adaptation method based on label propagation and cycle consistency to let the clusters of the features from the two domains overlap exactly and become clear for high accuracy.
Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications.
PuVAE: A Variational Autoencoder to Purify Adversarial Examples
Deep neural networks are widely used and exhibit excellent performance in many areas.
Ranked #2 on
Adversarial Defense against FGSM Attack
on MNIST
PixelSteganalysis: Pixel-wise Hidden Information Removal with Low Visual Degradation
We propose a DL based steganalysis technique that effectively removes secret images by restoring the distribution of the original images.
FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations.
HexaGAN: Generative Adversarial Nets for Real World Classification
We evaluate the classification performance (F1-score) of the proposed method with 20% missingness and confirm up to a 5% improvement in comparison with the performance of combinations of state-of-the-art methods.
AnomiGAN: Generative adversarial networks for anonymizing private medical data
We compared our method to state-of-the-art techniques and observed that our method preserves the same level of privacy as differential privacy (DP), but had better prediction results.
PixelSteganalysis: Destroying Hidden Information with a Low Degree of Visual Degradation
The cover image with the secret message is called a stego image.
FloWaveNet : A Generative Flow for Raw Audio
Most of modern text-to-speech architectures use a WaveNet vocoder for synthesizing a high-fidelity waveform audio, but there has been a limitation for practical applications due to its slow autoregressive sampling scheme.
Sound Audio and Speech Processing
Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks
The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability.
Security and Privacy Issues in Deep Learning
Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications.
Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector
We present a focal liver lesion detection model leveraged by custom-designed multi-phase computed tomography (CT) volumes, which reflects real-world clinical lesion detection practice using a Single Shot MultiBox Detector (SSD).
Robust Tumor Localization with Pyramid Grad-CAM
There have been various studies concerning automated lesion detection.
Deep Trustworthy Knowledge Tracing
Knowledge tracing (KT), a key component of an intelligent tutoring system, is a machine learning technique that estimates the mastery level of a student based on his/her past performance.
Energy-Efficient Inference Accelerator for Memory-Augmented Neural Networks on an FPGA
Memory-augmented neural networks (MANNs) are designed for question-answering tasks.
Deep Learning on Key Performance Indicators for Predictive Maintenance in SAP HANA
The experimental results with real-world data confirm the effectiveness of the system and models.
Mutual Suppression Network for Video Prediction using Disentangled Features
Video prediction can be performed by finding features in recent frames, and using them to generate approximations to upcoming frames.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
Reinforcement Learning based Recommender System using Biclustering Technique
A recommender system aims to recommend items that a user is interested in among many items.
Domain Adaptation Using Adversarial Learning for Autonomous Navigation
The objective of this study is to train an autonomous navigation model that uses a simulator (instead of real labeled data) and an inexpensive monocular camera.
Deep Recurrent Neural Network-Based Identification of Precursor microRNAs
MicroRNAs (miRNAs) are small non-coding ribonucleic acids (RNAs) which play key roles in post-transcriptional gene regulation.
Homomorphic Parameter Compression for Distributed Deep Learning Training
Distributed training of deep neural networks has received significant research interest, and its major approaches include implementations on multiple GPUs and clusters.
How Generative Adversarial Networks and Their Variants Work: An Overview
Generative Adversarial Networks (GAN) have received wide attention in the machine learning field for their potential to learn high-dimensional, complex real data distribution.
Adversarial Training for Disease Prediction from Electronic Health Records with Missing Data
Electronic health records (EHRs) have contributed to the computerization of patient records and can thus be used not only for efficient and systematic medical services, but also for research on biomedical data science.
Quantized Memory-Augmented Neural Networks
In this paper, we identify memory addressing (specifically, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge.
Polyphonic Music Generation with Sequence Generative Adversarial Networks
We propose an application of sequence generative adversarial networks (SeqGAN), which are generative adversarial networks for discrete sequence generation, for creating polyphonic musical sequences.
Sound Audio and Speech Processing
Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user.
DeepCCI: End-to-end Deep Learning for Chemical-Chemical Interaction Prediction
To guarantee the commutative property for homogeneous interaction, we apply model sharing and hidden representation merging techniques.
DNA Steganalysis Using Deep Recurrent Neural Networks
We compare our proposed method to various existing methods and biological sequence analysis methods implemented on top of our framework.
Building a Neural Machine Translation System Using Only Synthetic Parallel Data
Experiments on Czech-German and French-German translations demonstrate the efficacy of the proposed pseudo parallel corpus, which shows not only enhanced results for bidirectional translation tasks but also substantial improvement with the aid of a ground truth real parallel corpus.
Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets
Graphs provide a powerful means for representing complex interactions between entities.
Training IBM Watson using Automatically Generated Question-Answer Pairs
Under the assumption that using such an automatically generated dataset could relieve the burden of manual question-answer generation, we tried to use this dataset to train an instance of Watson and checked the training efficiency and accuracy.
An Efficient Approach to Boosting Performance of Deep Spiking Network Training
In order to eliminate this workaround, recently proposed is a new class of SNN named deep spiking networks (DSNs), which can be trained directly (without a mapping from conventional deep networks) by error backpropagation with stochastic gradient descent.
LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
In computer security, designing a robust intrusion detection system is one of the most fundamental and important problems.
Near-Data Processing for Differentiable Machine Learning Models
The second is the popularity of NAND flash-based solid-state drives (SSDs) containing multicore processors that can accommodate extra computation for data processing.
Neural Universal Discrete Denoiser
We present a new framework of applying deep neural networks (DNN) to devise a universal discrete denoiser.
deepMiRGene: Deep Neural Network based Precursor microRNA Prediction
Since microRNAs (miRNAs) play a crucial role in post-transcriptional gene regulation, miRNA identification is one of the most essential problems in computational biology.
deepTarget: End-to-end Learning Framework for microRNA Target Prediction using Deep Recurrent Neural Networks
MicroRNAs (miRNAs) are short sequences of ribonucleic acids that control the expression of target messenger RNAs (mRNAs) by binding them.
Deep Learning in Bioinformatics
In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics.
DeepSpark: A Spark-Based Distributed Deep Learning Framework for Commodity Clusters
The increasing complexity of deep neural networks (DNNs) has made it challenging to exploit existing large-scale data processing pipelines for handling massive data and parameters involved in DNN training.
DNA-Level Splice Junction Prediction using Deep Recurrent Neural Networks
A eukaryotic gene consists of multiple exons (protein coding regions) and introns (non-coding regions), and a splice junction refers to the boundary between a pair of exon and intron.
Manifold Regularized Deep Neural Networks using Adversarial Examples
Learning meaningful representations using deep neural networks involves designing efficient training schemes and well-structured networks.
NASCUP: Nucleic Acid Sequence Classification by Universal Probability
Motivated by the need for fast and accurate classification of unlabeled nucleotide sequences on a large scale, we developed NASCUP, a new classification method that captures statistical structures of nucleotide sequences by compact context-tree models and universal probability from information theory.
Genomics Information Theory Information Theory
Regularization and Kernelization of the Maximin Correlation Approach
Robust classification becomes challenging when each class consists of multiple subclasses.
