Search Results for author: Jong-Seok Lee

Found 33 papers, 13 papers with code

Curved Representation Space of Vision Transformers

no code implementations11 Oct 2022 Juyeop Kim, Junha Park, Songkuk Kim, Jong-Seok Lee

In this paper, we focus on the phenomenon that Transformers show higher robustness against corruptions than CNNs, while not being overconfident (in fact, we find Transformers are actually underconfident).

Analyzing Adversarial Robustness of Vision Transformers against Spatial and Spectral Attacks

no code implementations20 Aug 2022 Gihyun Kim, Jong-Seok Lee

Second, by noting that Transformers and CNNs rely on different types of information in images, we formulate an attack framework, called Fourier attack, as a tool for implementing flexible attacks, where an image can be attacked in the spectral domain as well as in the spatial domain.

Adversarial Robustness Image Classification

Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics

no code implementations20 Aug 2022 Hyeongnam Jang, Yeejin Lee, Jong-Seok Lee

We use the probability of being uncertain to define an intuitive metric of subjectivity.

Demystifying Randomly Initialized Networks for Evaluating Generative Models

no code implementations19 Aug 2022 Junghyuk Lee, Jun-Hyuk Kim, Jong-Seok Lee

Our results indicate that the features from random networks can evaluate generative models well similarly to those from trained networks, and furthermore, the two types of features can be used together in a complementary way.

Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks

no code implementations15 Dec 2021 Jaehui Hwang, huan zhang, Jun-Ho Choi, Cho-Jui Hsieh, Jong-Seok Lee

Another observation enabling our defense method is that adversarial perturbations on videos are sensitive to temporal destruction.

Action Recognition

Amicable Aid: Perturbing Images to Improve Classification Performance

no code implementations9 Dec 2021 Juyeop Kim, Jun-Ho Choi, Soobeom Jang, Jong-Seok Lee

While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification performance, which we call amicable aid.

Adversarial Attack Classification +2

Joint Global and Local Hierarchical Priors for Learned Image Compression

1 code implementation CVPR 2022 Jun-Hyuk Kim, Byeongho Heo, Jong-Seok Lee

Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG.

Image Compression

Light Lies: Optical Adversarial Attack

no code implementations18 Jun 2021 Kyulim Kim, JeongSoo Kim, Seungri Song, Jun-Ho Choi, Chulmin Joo, Jong-Seok Lee

We present experiments based on both simulation and a real hardware optical system, from which the feasibility of the proposed optical attack is demonstrated.

Adversarial Attack Classification +2

TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for GAN Evaluation

no code implementations30 Apr 2021 Junghyuk Lee, Jong-Seok Lee

The Frech\'et Inception distance is one of the most widely used metrics for evaluation of GANs, which assumes that the features from a trained Inception model for a set of images follow a normal distribution.

Density Estimation Image Generation

Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exits

1 code implementation1 Apr 2021 Hojung Lee, Jong-Seok Lee

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation.

Classification General Classification +1

Local Critic Training for Model-Parallel Learning of Deep Neural Networks

1 code implementation3 Feb 2021 Hojung Lee, Cho-Jui Hsieh, Jong-Seok Lee

We show that the proposed approach successfully decouples the update process of the layer groups for both convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

Emotional EEG Classification using Connectivity Features and Convolutional Neural Networks

no code implementations18 Jan 2021 Seong-Eun Moon, Chun-Jui Chen, Cho-Jui Hsieh, Jane-Ling Wang, Jong-Seok Lee

Convolutional neural networks (CNNs) are widely used to recognize the user's state through electroencephalography (EEG) signals.

Classification EEG +3

Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack

no code implementations ICCV 2021 Jaehui Hwang, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee

In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame attack that adds an inconspicuous perturbation to only a single frame of a given video clip.

Action Recognition Adversarial Attack

Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry

no code implementations15 Jul 2020 Kashmira Shinde, Jong-Seok Lee, Matthias Humt, Aydin Sezgin, Rudolph Triebel

This paper presents an end-to-end multi-modal learning approach for monocular Visual-Inertial Odometry (VIO), which is specifically designed to exploit sensor complementarity in the light of sensor degradation scenarios.

Inductive Bias

SRZoo: An integrated repository for super-resolution using deep learning

1 code implementation2 Jun 2020 Jun-Ho Choi, Jun-Hyuk Kim, Jong-Seok Lee

In addition, SRZoo provides platform-agnostic image reconstruction tools to obtain super-resolved images and evaluate the performance in place.

Image and Video Processing Multimedia

EmbraceNet for Activity: A Deep Multimodal Fusion Architecture for Activity Recognition

no code implementations29 Apr 2020 Jun-Ho Choi, Jong-Seok Lee

Human activity recognition using multiple sensors is a challenging but promising task in recent decades.

Human Activity Recognition

EEG-based Emotional Video Classification via Learning Connectivity Structure

1 code implementation28 May 2019 Soobeom Jang, Seong-Eun Moon, Jong-Seok Lee

Electroencephalography (EEG) is a useful way to implicitly monitor the users perceptual state during multimedia consumption.

Classification EEG +3

Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attacks

1 code implementation ICCV 2019 Jun-Ho Choi, huan zhang, Jun-Hyuk Kim, Cho-Jui Hsieh, Jong-Seok Lee

Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many computer vision applications.

Image Super-Resolution

Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network

2 code implementations30 Nov 2018 Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee

Recently, several deep learning-based image super-resolution methods have been developed by stacking massive numbers of layers.

Image Super-Resolution

MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution

3 code implementations29 Nov 2018 Jun-Hyuk Kim, Jun-Ho Choi, Manri Cheon, Jong-Seok Lee

Specifically, we propose a multi-path adaptive modulation block (MAMB), which is a lightweight yet effective residual block that adaptively modulates residual feature responses by fully exploiting their information via three paths.

Image Super-Resolution

Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality

1 code implementation13 Sep 2018 Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively.

Image Super-Resolution

Generative adversarial network-based image super-resolution using perceptual content losses

1 code implementation13 Sep 2018 Manri Cheon, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee

In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion.

Image Super-Resolution

EEG-based video identification using graph signal modeling and graph convolutional neural network

no code implementations12 Sep 2018 Soobeom Jang, Seong-Eun Moon, Jong-Seok Lee

This paper proposes a novel graph signal-based deep learning method for electroencephalography (EEG) and its application to EEG-based video identification.

EEG Electroencephalogram (EEG)

Evaluation of Preference of Multimedia Content using Deep Neural Networks for Electroencephalography

no code implementations11 Sep 2018 Seong-Eun Moon, Soobeom Jang, Jong-Seok Lee

Evaluation of quality of experience (QoE) based on electroencephalography (EEG) has received great attention due to its capability of real-time QoE monitoring of users.

EEG Electroencephalogram (EEG)

Local Critic Training of Deep Neural Networks

no code implementations ICLR 2019 Hojung Lee, Jong-Seok Lee

This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.