91 citations · 361 across the 26 of their papers we have counts for
26 papers
Quantile-Free Uncertainty Quantification in Graph Neural Networks
Soyoung park, Hwanjun Song, Sungsu Lim
Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often reli…
Adaptive Shortcut Debiasing for Online Continual Learning
Doyoung Kim, Dongmin Park, Yooju Shin +3
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred b…
Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise
Hwanjun Song, Minseok Kim, Jae-Gil Lee
Multi-label classification poses challenges due to imbalanced and noisy labels in training data. We propose a unified data augmentation method, named BalanceMix, to address these c…
Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy
Dongmin Park, Seola Choi, Doyoung Kim +2
Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though…
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
Doyoung Kim, Susik Yoon, Dongmin Park +4
In real-world continual learning (CL) scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies which are…
Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection
Hwanjun Song, Jihwan Bang
Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to dete…
Re-thinking Federated Active Learning based on Inter-class Diversity
SangMook Kim, Sangmin Bae, Hwanjun Song +1
Although federated learning has made awe-inspiring advances, most studies have assumed that the client's data are fully labeled. However, in a real-world scenario, every client may…
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems
Jemin Lee, Yongin Kwon, Sihyeong Park +3
Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the hig…
Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning
Dongmin Park, Yooju Shin, Jihwan Bang +3
Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few active learning studies have attempted to deal with this open-set noise for sample selection b…
e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce
Wonyoung Shin, Jonghun Park, Taekang Woo +3
Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce. As a backbone for online shopping platforms…
Time Is MattEr: Temporal Self-supervision for Video Transformers
Sukmin Yun, Jaehyung Kim, Dongyoon Han +3
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively ex…
Dataset Condensation via Efficient Synthetic-Data Parameterization
Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh +5
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning. Recent studies on dataset condens…
ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
Jaehoon Oh, Sungnyun Kim, Namgyu Ho +3
Cross-domain few-shot learning (CD-FSL), where there are few target samples under extreme differences between source and target domains, has recently attracted huge attention. Rece…
FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning
SangMook Kim, Wonyoung Shin, Soohyuk Jang +2
Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels. However, it is…
An Extendable, Efficient and Effective Transformer-based Object Detector
Hwanjun Song, Deqing Sun, Sanghyuk Chun +5
Transformers have been widely used in numerous vision problems especially for visual recognition and detection. Detection transformers are the first fully end-to-end learning syste…
Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
Jihwan Bang, Hyunseo Koh, Seulki Park +3
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, h…
Meta-Learning for Online Update of Recommender Systems
Minseok Kim, Hwanjun Song, Yooju Shin +3
Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over tim…
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
Jaehoon Oh, Sungnyun Kim, Namgyu Ho +3
Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scen…
Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective
Steven Euijong Whang, Yuji Roh, Hwanjun Song +1
Data-centric AI is at the center of a fundamental shift in software engineering where machine learning becomes the new software, powered by big data and computing infrastructure. H…
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Hwanjun Song, Deqing Sun, Sanghyuk Chun +5
Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object…
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
Seulki Park, Hwanjun Song, Daeho Um +3
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model. To overcome this issue, we propose a…
Robust Learning by Self-Transition for Handling Noisy Labels
Hwanjun Song, Minseok Kim, Dongmin Park +2
Real-world data inevitably contains noisy labels, which induce the poor generalization of deep neural networks. It is known that the network typically begins to rapidly memorize fa…
Learning from Noisy Labels with Deep Neural Networks: A Survey
Hwanjun Song, Minseok Kim, Dongmin Park +2
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of…
How does Early Stopping Help Generalization against Label Noise?
Hwanjun Song, Minseok Kim, Dongmin Park +1
Noisy labels are very common in real-world training data, which lead to poor generalization on test data because of overfitting to the noisy labels. In this paper, we claim that su…