6 citations · 15 across the 16 of their papers we have counts for
20 papers
Text-to-seed generation: Training-free open-vocabulary seeded semantic segmentation via re-purposing diffusion as text-guided seed generator
Kumju Jo, Heesun Jung, Sungyong Baik
Open-vocabulary semantic segmentation (OVSS) aims to segment image regions corresponding to arbitrary text queries. Although the Segment Anything Model (SAM) is a powerful foundati…
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
Jungwook Seo, Sangwon Son, Minjeong Kim +3
Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or localized oscillatory fluctuat…
Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization
Dain Kim, Jinseo Kim, Sungyong Baik
Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations ac…
SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
Junghun Oh, Sungyong Baik, Kyoung Mu Lee
Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with low-rank matrices. In this paper, we in…
BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
Jungwook Seo, Yoonsik Park, Changmin Lee +1
Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spu…
Find A Winning Sign: Sign Is All We Need to Win the Lottery
Junghun Oh, Sungyong Baik, Kyoung Mu Lee
The Lottery Ticket Hypothesis (LTH) posits the existence of a sparse subnetwork (a.k.a. winning ticket) that can generalize comparably to its over-parameterized counterpart when tr…
Deep Variational Bayesian Modeling of Haze Degradation Process
Eun Woo Im, Junsung Shin, Sungyong Baik +1
Relying on the representation power of neural networks, most recent works have often neglected several factors involved in haze degradation, such as transmission (the amount of lig…
CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning
Junghun Oh, Sungyong Baik, Kyoung Mu Lee
Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several chal…
Rethinking RGB Color Representation for Image Restoration Models
Jaerin Lee, JoonKyu Park, Sungyong Baik +1
Image restoration models are typically trained with a pixel-wise distance loss defined over the RGB color representation space, which is well known to be a source of blurry and unr…
MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields
Jaeyoung Chung, Kanggeon Lee, Sungyong Baik +1
Hinged on the representation power of neural networks, neural radiance fields (NeRF) have recently emerged as one of the promising and widely applicable methods for 3D object and s…
CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
Cheeun Hong, Sungyong Baik, Heewon Kim +2
Despite breakthrough advances in image super-resolution (SR) with convolutional neural networks (CNNs), SR has yet to enjoy ubiquitous applications due to the high computational co…
Pyramidal Attention for Saliency Detection
Tanveer Hussain, Abbas Anwar, Saeed Anwar +2
Salient object detection (SOD) extracts meaningful contents from an input image. RGB-based SOD methods lack the complementary depth clues; hence, providing limited performance for…
Batch Normalization Tells You Which Filter is Important
Junghun Oh, Heewon Kim, Sungyong Baik +2
The goal of filter pruning is to search for unimportant filters to remove in order to make convolutional neural networks (CNNs) efficient without sacrificing the performance in the…
Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
Sungyong Baik, Janghoon Choi, Heewon Kim +3
In few-shot learning scenarios, the challenge is to generalize and perform well on new unseen examples when only very few labeled examples are available for each task. Model-agnost…
Searching for Controllable Image Restoration Networks
Heewon Kim, Sungyong Baik, Myungsub Choi +2
Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks. However, existing methods requi…
Meta-Learning with Adaptive Hyperparameters
Sungyong Baik, Myungsub Choi, Janghoon Choi +2
Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodol…
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks
Cheeun Hong, Heewon Kim, Sungyong Baik +2
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe perfor…
Domain Adaptation of Learned Features for Visual Localization
Sungyong Baik, Hyo Jin Kim, Tianwei Shen +3
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons. Recent learned local features based on deep neural networks have…
Scene-Adaptive Video Frame Interpolation via Meta-Learning
Myungsub Choi, Janghoon Choi, Sungyong Baik +2
Video frame interpolation is a challenging problem because there are different scenarios for each video depending on the variety of foreground and background motion, frame rate, an…
Learning to Forget for Meta-Learning
Sungyong Baik, Seokil Hong, Kyoung Mu Lee
Few-shot learning is a challenging problem where the goal is to achieve generalization from only few examples. Model-agnostic meta-learning (MAML) tackles the problem by formulatin…