25 citations · 87 across the 15 of their papers we have counts for
15 papers
Hierarchical Self-Supervised Representation Learning Framework for Multivariate Time Series Grounded in ECG Analysis
Siwon Kim
Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distribution. Under such circumsta…
Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation
HyunGi Kim, Siwon Kim, Jisoo Mok +1
Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling. Nonetheless, the non-stationarity of…
Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
Jaihyun Lew, Soohyuk Jang, Jaehoon Lee +6
Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success…
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
Eunji Kim, Siwon Kim, Minjun Park +2
Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, whic…
GrounDial: Human-norm Grounded Safe Dialog Response Generation
Siwon Kim, Shuyang Dai, Mohammad Kachuee +3
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. Previou…
ProPILE: Probing Privacy Leakage in Large Language Models
Siwon Kim, Sangdoo Yun, Hwaran Lee +3
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PI…
Probabilistic Concept Bottleneck Models
Eunji Kim, Dahuin Jung, Sangha Park +2
Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept predicti…
On the Impact of Knowledge Distillation for Model Interpretability
Hyeongrok Han, Siwon Kim, Hyun-Soo Choi +1
Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improv…
Grounding Visual Representations with Texts for Domain Generalization
Seonwoo Min, Nokyung Park, Siwon Kim +2
Reducing the representational discrepancy between source and target domains is a key component to maximize the model generalization. In this work, we advocate for leveraging natura…
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Eunji Kim, Siwon Kim, Jungbeom Lee +2
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class…
Towards a Rigorous Evaluation of Time-series Anomaly Detection
Siwon Kim, Kukjin Choi, Hyun-Soo Choi +2
In recent years, proposed studies on time-series anomaly detection (TAD) report high F1 scores on benchmark TAD datasets, giving the impression of clear improvements in TAD. Howeve…
XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations
Eunji Kim, Siwon Kim, Minji Seo +1
Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases. However, existing methods only provide predictions witho…
Interpretation of NLP models through input marginalization
Siwon Kim, Jihun Yi, Eunji Kim +1
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…
Information-Theoretic Visual Explanation for Black-Box Classifiers
Jihun Yi, Eunji Kim, Siwon Kim +1
In this work, we attempt to explain the prediction of any black-box classifier from an information-theoretic perspective. For each input feature, we compare the classifier outputs…
Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information
Seonwoo Min, Seunghyun Park, Siwon Kim +3
Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modelin…