Search Results for author:
Found 34 papers, 14 papers with code
Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability
With the advancement of generative models, the assessment of generated images becomes more and more important.
ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection
First, we propose a novel feature extraction method suitable for the Vision Transformer backbone, called masking with overlapped area (MOA) module.
Ranked #5 on
Human-Object Interaction Detection
on HICO-DET
Similarity of Neural Architectures using Adversarial Attack Transferability
In recent years, many deep neural architectures have been developed for image classification.
Curved Representation Space of Vision Transformers
In this paper, we focus on the phenomenon that Transformers show higher robustness against corruptions than CNNs, while not being overconfident.
Modeling, Quantifying, and Predicting Subjectivity of Image Aesthetics
We use the probability of being uncertain to define an intuitive metric of subjectivity.
Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective
This paper proposes an additional perspective that explores the adversarial robustness of Transformers against frequency-selective perturbations in the spectral domain.
Demystifying Randomly Initialized Networks for Evaluating Generative Models
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
Recently, video-based action recognition methods using convolutional neural networks (CNNs) achieve remarkable recognition performance.
Amicable Aid: Perturbing Images to Improve Classification Performance
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.
Joint Global and Local Hierarchical Priors for Learned Image Compression
Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG.
Light Lies: Optical Adversarial Attack
We present experiments based on both simulation and a real hardware optical system, from which the feasibility of the proposed optical attack is demonstrated.
TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for GAN Evaluation
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.
Deep Image Destruction: Vulnerability of Deep Image-to-Image Models against Adversarial Attacks
Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated.
Students are the Best Teacher: Exit-Ensemble Distillation with Multi-Exits
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.
Local Critic Training for Model-Parallel Learning of Deep Neural Networks
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
Convolutional neural networks (CNNs) are widely used to recognize the user's state through electroencephalography (EEG) signals.
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack
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.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry
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.
SRZoo: An integrated repository for super-resolution using deep learning
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
Human activity recognition using multiple sensors is a challenging but promising task in recent decades.
EEG-based Emotional Video Classification via Learning Connectivity Structure
Electroencephalography (EEG) is a useful way to implicitly monitor the users perceptual state during multimedia consumption.
EmbraceNet: A robust deep learning architecture for multimodal classification
Classification using multimodal data arises in many machine learning applications.
Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attacks
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.
Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
Recently, several deep learning-based image super-resolution methods have been developed by stacking massive numbers of layers.
Ranked #27 on
Image Super-Resolution
on BSD100 - 4x upscaling
MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution
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.
Ranked #28 on
Image Super-Resolution
on BSD100 - 4x upscaling
Generative adversarial network-based image super-resolution using perceptual content losses
In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion.
Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality
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.
Ranked #51 on
Image Super-Resolution
on BSD100 - 4x upscaling
Convolutional Neural Network Approach for EEG-based Emotion Recognition using Brain Connectivity and its Spatial Information
Emotion recognition based on electroencephalography (EEG) has received attention as a way to implement human-centric services.
EEG-based video identification using graph signal modeling and graph convolutional neural network
This paper proposes a novel graph signal-based deep learning method for electroencephalography (EEG) and its application to EEG-based video identification.
Evaluation of Preference of Multimedia Content using Deep Neural Networks for Electroencephalography
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.
Local Critic Training of Deep Neural Networks
This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training.
