Search Results for author: Seong Tae Kim

Found 35 papers, 13 papers with code

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

1 code implementation CVPR 2024 Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.

Decoder Dense Video Captioning +2

WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts

1 code implementation29 Feb 2024 Yong Hyun Ahn, Hyeon Bae Kim, Seong Tae Kim

Recent advancements in neural networks have showcased their remarkable capabilities across various domains.

OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning

no code implementations22 Jan 2024 Chu Myaet Thwal, Minh N. H. Nguyen, Ye Lin Tun, Seong Tae Kim, My T. Thai, Choong Seon Hong

Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy.

Computational Efficiency Federated Learning

Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability

no code implementations26 Mar 2023 Soyoun Won, Sung-Ho Bae, Seong Tae Kim

Data augmentation strategies are actively used when training deep neural networks (DNNs).

Data Augmentation

LINe: Out-of-Distribution Detection by Leveraging Important Neurons

1 code implementation CVPR 2023 Yong Hyun Ahn, Gyeong-Moon Park, Seong Tae Kim

In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data.

Autonomous Driving Out-of-Distribution Detection

Improved Abdominal Multi-Organ Segmentation via 3D Boundary-Constrained Deep Neural Networks

1 code implementation9 Oct 2022 Samra Irshad, Douglas P. S. Gomes, Seong Tae Kim

To address the problem of abdominal multi-organ segmentation, we train the 3D encoder-decoder network to simultaneously segment the abdominal organs and their corresponding boundaries in CT scans via multi-task learning.

Decoder Image Segmentation +5

Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning

no code implementations25 Jul 2022 Felix Buchert, Nassir Navab, Seong Tae Kim

By considering the consistency information with the diversity in the consistency-based embedding scheme, the proposed method could select more informative samples for labeling in the semi-supervised learning setting.

Active Learning Representation Learning

Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models

no code implementations4 Apr 2022 Ashkan Khakzar, Yawei Li, Yang Zhang, Mirac Sanisoglu, Seong Tae Kim, Mina Rezaei, Bernd Bischl, Nassir Navab

One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced.

Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models

1 code implementation4 Apr 2021 Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger, Icxel Valeriano Quiroz, Nikolaus Pinger, Soroosh Baselizadeh, Seong Tae Kim, Nassir Navab

We present our findings using publicly available chest pathologies (CheXpert, NIH ChestX-ray8) and COVID-19 datasets (BrixIA, and COVID-19 chest X-ray segmentation dataset).

COVID-19 Diagnosis

GLOWin: A Flow-based Invertible Generative Framework for Learning Disentangled Feature Representations in Medical Images

no code implementations19 Mar 2021 Aadhithya Sankar, Matthias Keicher, Rami Eisawy, Abhijeet Parida, Franz Pfister, Seong Tae Kim, Nassir Navab

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models that require a large number of labelled or unlabelled data.

Disentanglement

Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs

1 code implementation12 Mar 2021 Seong Tae Kim, Leili Goli, Magdalini Paschali, Ashkan Khakzar, Matthias Keicher, Tobias Czempiel, Egon Burian, Rickmer Braren, Nassir Navab, Thomas Wendler

Chest computed tomography (CT) has played an essential diagnostic role in assessing patients with COVID-19 by showing disease-specific image features such as ground-glass opacity and consolidation.

Computed Tomography (CT) COVID-19 Image Segmentation +2

OperA: Attention-Regularized Transformers for Surgical Phase Recognition

no code implementations5 Mar 2021 Tobias Czempiel, Magdalini Paschali, Daniel Ostler, Seong Tae Kim, Benjamin Busam, Nassir Navab

In this paper we introduce OperA, a transformer-based model that accurately predicts surgical phases from long video sequences.

Surgical phase recognition

Self-Supervised Out-of-Distribution Detection in Brain CT Scans

no code implementations10 Nov 2020 Abinav Ravi Venkatakrishnan, Seong Tae Kim, Rami Eisawy, Franz Pfister, Nassir Navab

To address these issues, recently, unsupervised deep anomaly detection methods that train the model on large-sized normal scans and detect abnormal scans by calculating reconstruction error have been reported.

Anomaly Detection Out-of-Distribution Detection +1

Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack

no code implementations21 May 2020 Hakmin Lee, Hong Joo Lee, Seong Tae Kim, Yong Man Ro

After the ensemble models are trained, it can hide the gradient efficiently and avoid the gradient-based attack by the random layer sampling method.

Adversarial Attack Adversarial Robustness

Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation

no code implementations21 May 2020 Hong Joo Lee, Seong Tae Kim, Hakmin Lee, Nassir Navab, Yong Man Ro

Experimental results show that the proposed method could provide useful uncertainty information by Bayesian approximation with the efficient ensemble model generation and improve the predictive performance.

Segmentation

Confident Coreset for Active Learning in Medical Image Analysis

no code implementations5 Apr 2020 Seong Tae Kim, Farrukh Mushtaq, Nassir Navab

Active learning is one of the solutions to this problem where an active learner is designed to indicate which samples need to be annotated to effectively train a target model.

Active Learning

TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks

2 code implementations24 Mar 2020 Tobias Czempiel, Magdalini Paschali, Matthias Keicher, Walter Simson, Hubertus Feussner, Seong Tae Kim, Nassir Navab

Automatic surgical phase recognition is a challenging and crucial task with the potential to improve patient safety and become an integral part of intra-operative decision-support systems.

Surgical phase recognition

Force-Ultrasound Fusion: Bringing Spine Robotic-US to the Next "Level"

1 code implementation26 Feb 2020 Maria Tirindelli, Maria Victorova, Javier Esteban, Seong Tae Kim, David Navarro-Alarcon, Yong Ping Zheng, Nassir Navab

Processed force and ultrasound data are fused using a 1D Convolutional Network to compute the location of the vertebral levels.

Improving Feature Attribution through Input-specific Network Pruning

no code implementations25 Nov 2019 Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab

Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks.

Network Pruning

Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis

no code implementations10 Jun 2019 Hyebin Lee, Seong Tae Kim, Yong Man Ro

The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance.

Decision Making Sentence

Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation

no code implementations17 Sep 2018 Jae-Hyeok Lee, Seong Tae Kim, Hakmin Lee, Yong Man Ro

In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required.

Image Generation

ICADx: Interpretable computer aided diagnosis of breast masses

no code implementations23 May 2018 Seong Tae Kim, Hakmin Lee, Hak Gu Kim, Yong Man Ro

In this paper, we investigate interpretability in CADx with the proposed interpretable CADx (ICADx) framework.

Generative Adversarial Network

Facial Dynamics Interpreter Network: What are the Important Relations between Local Dynamics for Facial Trait Estimation?

no code implementations ECCV 2018 Seong Tae Kim, Yong Man Ro

In this paper, a novel deep learning approach, named facial dynamics interpreter network, has been proposed to interpret the important relations between local dynamics for estimating facial traits from expression sequence.

Age Estimation Gender Classification +1

Convolution with Logarithmic Filter Groups for Efficient Shallow CNN

no code implementations31 Jul 2017 Tae Kwan Lee, Wissam J. Baddar, Seong Tae Kim, Yong Man Ro

Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency.

Classification Facial Expression Recognition +2

EvaluationNet: Can Human Skill be Evaluated by Deep Networks?

no code implementations31 May 2017 Seong Tae Kim, Yong Man Ro

In order to improve the effectiveness of the learning with instructional video, observation and evaluation of the activity are required.

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