Search Results for author:
Found 110 papers, 42 papers with code
Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representations
To tackle this problem, previous work on code summarization, the task of automatically generating code description given a piece of code reported that an auxiliary learning model trained to produce API (Application Programming Interface) embeddings showed promising results when applied to a downstream, code summarization model.
PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
Document-level relation extraction (DocRE) aims to extract relations of all entity pairs in a document.
Learning to Diversify Neural Text Generation via Degenerative Model
We then enhance the diversity of the second model by focusing on patterns that the first model fails to learn.
SideGAN: 3D-Aware Generative Model for Improved Side-View Image Synthesis
In this paper, we propose SideGAN, a novel 3D GAN training method to generate photo-realistic images irrespective of the camera pose, especially for faces of side-view angles.
MagiCapture: High-Resolution Multi-Concept Portrait Customization
The main challenge with this task is the absence of ground truth for the composed concepts, leading to a reduction in the quality of the final output and an identity shift of the source subject.
Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model
Our main strategy is to construct the 3D avatar in Neural Radiance Fields (NeRF) optimized with a set of controlled viewpoint-aware images that we generate from ControlNet, whose condition input is the depth map extracted from the input video.
Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems
In this work, we revisited experiments on IRS with review datasets and compared RL-based models with a simple reward model that greedily recommends the item with the highest one-step reward.
ST-RAP: A Spatio-Temporal Framework for Real Estate Appraisal
In this paper, we introduce ST-RAP, a novel Spatio-Temporal framework for Real estate APpraisal.
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference.
Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesis
Our experiments reveal that we can guide text-to-image generation models to be aware of the semantics of different image regions, by training the model to generate semantic labels for each pixel.
Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction
Shourcut-V2V avoids full inference for every neighboring video frame by approximating the intermediate features of a current frame from those of the previous frame.
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization
To be more specific, entropy minimization attempts to raise the confidence values of an individual sample's prediction, but individual confidence values may rise or fall due to the influence of signals from numerous other predictions (i. e., wisdom of crowds).
FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields
To do so, we first train a scene manipulator, a latent code-conditional deformable NeRF, over a dynamic scene to control a face deformation using the latent code.
PixelHuman: Animatable Neural Radiance Fields from Few Images
In this paper, we propose PixelHuman, a novel human rendering model that generates animatable human scenes from a few images of a person with unseen identity, views, and poses.
HistRED: A Historical Document-Level Relation Extraction Dataset
To demonstrate the usefulness of our dataset, we propose a bilingual RE model that leverages both Korean and Hanja contexts to predict relations between entities.
Local 3D Editing via 3D Distillation of CLIP Knowledge
Specifically, we present three add-on modules of LENeRF, the Latent Residual Mapper, the Attention Field Network, and the Deformation Network, which are jointly used for local manipulations of 3D features by estimating a 3D attention field.
Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints
The effects of PLUMCOT are shown to be remarkable in "unseen" constraints.
Enhancing Generalization and Plasticity for Sample Efficient Reinforcement Learning
In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky.
On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
To address this issue, we propose a novel URL framework that causally predicts future states while increasing the dimension of the latent manifold by decorrelating the features in the latent space.
DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation
Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem.
Improving Scene Text Recognition for Character-Level Long-Tailed Distribution
However, STR models show a large performance degradation on languages with a numerous number of characters (e. g., Chinese and Korean), especially on characters that rarely appear due to the long-tailed distribution of characters in such languages.
Reference-based Image Composition with Sketch via Structure-aware Diffusion Model
Recent remarkable improvements in large-scale text-to-image generative models have shown promising results in generating high-fidelity images.
RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage
However, we observed that previous approaches still suffer from source attribute leakage, where the source image's attributes interfere with the target image's.
Perspective Projection-Based 3D CT Reconstruction from Biplanar X-rays
X-ray computed tomography (CT) is one of the most common imaging techniques used to diagnose various diseases in the medical field.
Deep Imbalanced Time-series Forecasting via Local Discrepancy Density
Based on our findings, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states.
TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
In this paper, we identify that CBN and TBN are in a trade-off relationship and present a new test-time normalization (TTN) method that interpolates the statistics by adjusting the importance between CBN and TBN according to the domain-shift sensitivity of each BN layer.
3D-Aware Generative Model for Improved Side-View Image Synthesis
In this paper, we propose SideGAN, a novel 3D GAN training method to generate photo-realistic images irrespective of the camera pose, especially for faces of side-view angles.
ReFu: Refine and Fuse the Unobserved View for Detail-Preserving Single-Image 3D Human Reconstruction
Single-image 3D human reconstruction aims to reconstruct the 3D textured surface of the human body given a single image.
Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task
To overcome these limitations, this paper proposes a simple but efficient method for generating adversarial negative responses leveraging a large-scale language model.
WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting
Time series forecasting has become a critical task due to its high practicality in real-world applications such as traffic, energy consumption, economics and finance, and disease analysis.
Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
Existing deep interactive colorization models have focused on ways to utilize various types of interactions, such as point-wise color hints, scribbles, or natural-language texts, as methods to reflect a user's intent at runtime.
Enemy Spotted: in-game gun sound dataset for gunshot classification and localization
By exploiting the advantage of the game environment, we construct a gunshot dataset, namely BGG, for the firearm classification and gunshot localization tasks.
PePe: Personalized Post-editing Model utilizing User-generated Post-edits
Incorporating personal preference is crucial in advanced machine translation tasks.
Morphology-Aware Interactive Keypoint Estimation
To fully automate this procedure, deep-learning-based methods have been widely proposed and have achieved high performance in detecting keypoints in medical images.
DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation
We call the unwanted correlations "data biases," and the visual features causing data biases "bias factors."
Residual Correction in Real-Time Traffic Forecasting
Extensive experiments on METR-LA and PEMS-BAY demonstrate that our ResCAL can correctly capture the correlation of errors and correct the failures of various traffic forecasting models in event situations.
Reweighting Strategy based on Synthetic Data Identification for Sentence Similarity
To analyze this, we first train a classifier that identifies machine-written sentences, and observe that the linguistic features of the sentences identified as written by a machine are significantly different from those of human-written sentences.
Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment
Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle.
A Visual Analytics System for Improving Attention-based Traffic Forecasting Models
With deep learning (DL) outperforming conventional methods for different tasks, much effort has been devoted to utilizing DL in various domains.
Towards Accurate Open-Set Recognition via Background-Class Regularization
To effectively solve the OSR problem, previous studies attempted to limit latent feature space and reject data located outside the limited space via offline analyses, e. g., distance-based feature analyses, or complicated network architectures.
iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
It is essential for point-interactive colorization methods to appropriately propagate user-provided colors (i. e., user hints) in the entire image to obtain a reasonably colorized image with minimal user effort.
Ranked #1 on
Point-interactive Image Colorization
on Oxford 102 Flowers
(PSNR@1 metric)
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing item.
Ranked #1 on
Virtual Try-on
on VITON-HD
HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting
Hairstyle transfer is the task of modifying a source hairstyle to a target one.
Mining Multi-Label Samples from Single Positive Labels
Therefore, in this study we explore the practical setting called the single positive setting, where each data instance is annotated by only one positive label with no explicit negative labels.
Improving Evaluation of Debiasing in Image Classification
Based on such issues, this paper 1) proposes an evaluation metric `Align-Conflict (AC) score' for the tuning criterion, 2) includes experimental settings with low bias severity and shows that they are yet to be explored, and 3) unifies the standardized experimental settings to promote fair comparisons between debiasing methods.
CAFA: Class-Aware Feature Alignment for Test-Time Adaptation
That is, a model does not have a chance to learn test data in a class-discriminative manner, which was feasible in other adaptation tasks (\textit{e. g.,} unsupervised domain adaptation) via supervised losses on the source data.
Revisiting the Importance of Amplifying Bias for Debiasing
$f_B$ is trained to focus on bias-aligned samples (i. e., overfitted to the bias) while $f_D$ is mainly trained with bias-conflicting samples by concentrating on samples which $f_B$ fails to learn, leading $f_D$ to be less susceptible to the dataset bias.
DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games
To alleviate this problem, we propose DraftRec, a novel hierarchical model which recommends characters by considering each player's champion preferences and the interaction between the players.
3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications.
Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE
In order to perform unconditional video generation, we must learn the distribution of the real-world videos.
CG-NeRF: Conditional Generative Neural Radiance Fields
While recent NeRF-based generative models achieve the generation of diverse 3D-aware images, these approaches have limitations when generating images that contain user-specified characteristics.
Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)
Image-based virtual try-on provides the capacity to transfer a clothing item onto a photo of a given person, which is usually accomplished by warping the item to a given human pose and adjusting the warped item to the person.
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
We present a novel Animation CelebHeads dataset (AnimeCeleb) to address an animation head reenactment.
AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain
During the fine-tuning phase of transfer learning, the pretrained vocabulary remains unchanged, while model parameters are updated.
Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity.
Natural Attribute-based Shift Detection
Despite the impressive performance of deep networks in vision, language, and healthcare, unpredictable behaviors on samples from the distribution different than the training distribution cause severe problems in deployment.
Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift
The former normalizes the input to fix its distribution in terms of the mean and variance, while the latter returns the output to the original distribution.
Decoupled Kernel Neural Processes: Neural Network-Parameterized Stochastic Processes using Explicit Data-driven Kernel
To address this, we introduce a new neural stochastic processes, Decoupled Kernel Neural Processes (DKNPs), which explicitly learn a separate mean and kernel function to directly model the covariance between output variables in a data-driven manner.
Distance-Based Background Class Regularization for Open-Set Recognition
In this paper, we propose a novel distance-based BCR method suitable for OSR, which limits the feature space of known-class data in a class-wise manner and then makes background-class samples located far away from the limited feature space.
BiaSwap: Removing dataset bias with bias-tailored swapping augmentation
Although previous approaches pre-define the type of dataset bias to prevent the network from learning it, recognizing the bias type in the real dataset is often prohibitive.
Ranked #3 on
Facial Attribute Classification
on bFFHQ
MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation
Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest.
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
However, the distribution of max logits of each predicted class is significantly different from each other, which degrades the performance of identifying unexpected objects in urban-scene segmentation.
Ranked #4 on
Anomaly Detection
on Lost and Found
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images
In multi-modal dialogue systems, it is important to allow the use of images as part of a multi-turn conversation.
Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects
Deep neural networks for automatic image colorization often suffer from the color-bleeding artifact, a problematic color spreading near the boundaries between adjacent objects.
Learning Debiased Representation via Disentangled Feature Augmentation
To this end, our method learns the disentangled representation of (1) the intrinsic attributes (i. e., those inherently defining a certain class) and (2) bias attributes (i. e., peripheral attributes causing the bias), from a large number of bias-aligned samples, the bias attributes of which have strong correlation with the target variable.
Not Just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction
While the existing cycle-consistency loss ensures that the image can be translated back, our approach makes the model further preserve the attribute-irrelevant regions even in a single translation to another domain by using the Grad-CAM output computed from the discriminator.
An Empirical Experiment on Deep Learning Models for Predicting Traffic Data
For example, it is difficult to figure out which models provide state-of-the-art performance, as recently proposed models have often been evaluated with different datasets and experiment environments.
Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation
Understanding voluminous historical records provides clues on the past in various aspects, such as social and political issues and even natural science facts.
VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization
The task of image-based virtual try-on aims to transfer a target clothing item onto the corresponding region of a person, which is commonly tackled by fitting the item to the desired body part and fusing the warped item with the person.
Ranked #2 on
Virtual Try-on
on VITON-HD
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving.
K-Hairstyle: A Large-scale Korean Hairstyle Dataset for Virtual Hair Editing and Hairstyle Classification
In response, we introduce a novel large-scale Korean hairstyle dataset, K-hairstyle, containing 500, 000 high-resolution images.
Stego Networks: Information Hiding on Deep Neural Networks
This paper considers neural networks as novel steganographic cover media, which we call stego networks, that can be used to hide one's secret messages.
Learning Representations by Contrasting Clusters While Bootstrapping Instances
Learning visual representations using large-scale unlabelled images is a holy grail for most of computer vision tasks.
Learning to Generate Questions by Recovering Answer-containing Sentences
We evaluate our method against existing ones in terms of the quality of generated questions as well as the fine-tuned MRC model accuracy after training on the data synthetically generated by our method.
Ranked #3 on
Question Generation
on SQuAD1.1
(using extra training data)
Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment
We evaluate the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques with a new evaluation framework.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
Knowledge Graph-based Question Answering with Electronic Health Records
Question Answering (QA) is a widely-used framework for developing and evaluating an intelligent machine.
Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning
To address this issue, this paper presents a novel meta-learning algorithm for unsupervised neural machine translation (UNMT) that trains the model to adapt to another domain by utilizing only a small amount of training data.
Neural Ordinary Differential Equations for Intervention Modeling
By interpreting the forward dynamics of the latent representation of neural networks as an ordinary differential equation, Neural Ordinary Differential Equation (Neural ODE) emerged as an effective framework for modeling a system dynamics in the continuous time domain.
Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e. g., increasing the frame rate of the more dynamic portion of the video as well as handling missing video frames).
HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks
HyperTendril takes a novel approach to effectively steering hyperparameter optimization through an iterative, interactive tuning procedure that allows users to refine the search spaces and the configuration of the AutoML method based on their own insights from given results.
Towards Lightweight Lane Detection by Optimizing Spatial Embedding
This paper addresses the problem that pixel embedding in proposal-free instance segmentation based lane detection is difficult to optimize.
Ranked #10 on
Lane Detection
on TuSimple
Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence
However, it is difficult to prepare for a training data set that has a sufficient amount of semantically meaningful pairs of images as well as the ground truth for a colored image reflecting a given reference (e. g., coloring a sketch of an originally blue car given a reference green car).
NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension
Real-world question answering systems often retrieve potentially relevant documents to a given question through a keyword search, followed by a machine reading comprehension (MRC) step to find the exact answer from them.
Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks
This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban-scene images.
Ranked #13 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
Exploring Unlabeled Faces for Novel Attribute Discovery
Despite remarkable success in unpaired image-to-image translation, existing systems still require a large amount of labeled images.
Unpaired Image Translation via Adaptive Convolution-based Normalization
Disentangling content and style information of an image has played an important role in recent success in image translation.
ST-GRAT: A Novel Spatio-temporal Graph Attention Network for Accurately Forecasting Dynamically Changing Road Speed
Predicting road traffic speed is a challenging task due to different types of roads, abrupt speed change and spatial dependencies between roads; it requires the modeling of dynamically changing spatial dependencies among roads and temporal patterns over long input sequences.
NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions
Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL.
Learning De-biased Representations with Biased Representations
This tactic is feasible in many scenarios where it is much easier to define a set of biased representations than to define and quantify bias.
Progressive Upsampling Audio Synthesis via Effective Adversarial Training
This paper proposes a novel generative model called PUGAN, which progressively synthesizes high-quality audio in a raw waveform.
ASGen: Answer-containing Sentence Generation to Pre-Train Question Generator for Scale-up Data in Question Answering
We evaluate the question generation capability of our method by comparing the BLEU score with existing methods and test our method by fine-tuning the MRC model on the downstream MRC data after training on synthetic data.
SANVis: Visual Analytics for Understanding Self-Attention Networks
Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many other applications.
What and Where to Translate: Local Mask-based Image-to-Image Translation
First, those methods extract style from an entire exemplar which includes noisy information, which impedes a translation model from properly extracting the intended style of the exemplar.
Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks
Despite recent advancements in deep learning-based automatic colorization, they are still limited when it comes to few-shot learning.
Local Image-to-Image Translation via Pixel-wise Highway Adaptive Instance Normalization
Recently, image-to-image translation has seen a significant success.
MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation
First, we use a content representation from the source domain conditioned on a style representation from the target domain.
Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation
However, applying this approach in image translation is computationally intensive and error-prone due to the expensive time complexity and its non-trivial backpropagation.
Interpreting Models by Allowing to Ask
Questions convey information about the questioner, namely what one does not know.
MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller
Machine reading comprehension helps machines learn to utilize most of the human knowledge written in the form of text.
Ranked #22 on
Question Answering
on TriviaQA
(using extra training data)
Neural Distribution Learning for generalized time-to-event prediction
Predicting the time to the next event is an important task in various domains.
Question-Aware Sentence Gating Networks for Question and Answering
Machine comprehension question answering, which finds an answer to the question given a passage, involves high-level reasoning processes of understanding and tracking the relevant contents across various semantic units such as words, phrases, and sentences in a document.
RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
Therefore, our design study aims to provide a visual analytics solution to increase interpretability and interactivity of RNNs via a joint effort of medical experts, artificial intelligence scientists, and visual analytics researchers.
MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation
Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images.
Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation
This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette.
Visual Analytics for Explainable Deep Learning
Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever.
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.
Ranked #1 on
Image-to-Image Translation
on RaFD
(using extra training data)
MMGAN: Manifold Matching Generative Adversarial Network
MMGAN finds two manifolds representing the vector representations of real and fake images.
End-to-End Prediction of Buffer Overruns from Raw Source Code via Neural Memory Networks
Our experimental results using source codes demonstrate that our proposed model is capable of accurately detecting simple buffer overruns.
PixelSNE: Visualizing Fast with Just Enough Precision via Pixel-Aligned Stochastic Neighbor Embedding
Embedding and visualizing large-scale high-dimensional data in a two-dimensional space is an important problem since such visualization can reveal deep insights out of complex data.
