4 citations · 5 across the 16 of their papers we have counts for
18 papers
Isotropic Embedding Perturbations for Robust Vision Language Encoders
Hyesong Choi, Daeun Kim, Song Park +5
Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer stro…
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
Jihyeon Kim, Sohee Kim, Soosan Lee +3
Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularly in person-centric and partia…
AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers
Semi Lee, Hyejin Go, Hyesong Choi
The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token red…
The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP
Kahyeon Nam, Hyesong Choi
Deploying Vision-Language Models on resource-constrained hardware typically requires INT8 quantization, but in joint-embedding architectures such as CLIP this introduces a failure…
What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining
Hyejin Go, Semi Lee, Hyesong Choi
CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignment. We show that this signal…
Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
Jiyeong Kim, Yerim So, Hyesong Choi +2
Unified Multimodal Models (UMMs) have emerged as a promising paradigm that integrates multimodal understanding and generation within a unified modeling framework. However, current…
RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
Jueun Ko, Hyewon Park, Hyesong Choi +1
Stereo Depth Estimation in real-world environments poses significant challenges due to dynamic domain shifts, sparse or unreliable supervision, and the high cost of acquiring dense…
TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning
Seungmin Baek, Soyul Lee, Hayeon Jo +2
Transfer learning paradigm has driven substantial advancements in various vision tasks. However, as state-of-the-art models continue to grow, classical full fine-tuning often becom…
Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
Hyesong Choi, Daeun Kim, Sungmin Cha +2
In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of la…
MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
Jihye Ahn, Hyesong Choi, Soomin Kim +1
In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still la…
UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
Soomin Kim, Hyesong Choi, Jihye Ahn +1
Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches. This is m…
SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
Sumin Son, Hyesong Choi, Dongbo Min
Masked Image Modeling (MIM) techniques have redefined the landscape of computer vision, enabling pre-trained models to achieve exceptional performance across a broad spectrum of ta…
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation
Hayeon Jo, Hyesong Choi, Minhee Cho +1
Transfer learning based on full fine-tuning (FFT) of the pre-trained encoder and task-specific decoder becomes increasingly complex as deep models grow exponentially. Parameter eff…
Collaborative Learning for Enhanced Unsupervised Domain Adaptation
Minhee Cho, Hyesong Choi, Hayeon Jo +1
Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain. However, curre…
Emerging Property of Masked Token for Effective Pre-training
Hyesong Choi, Hunsang Lee, Seyoung Joung +3
Driven by the success of Masked Language Modeling (MLM), the realm of self-supervised learning for computer vision has been invigorated by the central role of Masked Image Modeling…
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
Hyesong Choi, Hyejin Park, Kwang Moo Yi +2
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Mod…
Sequential Cross Attention Based Multi-task Learning
Sunkyung Kim, Hyesong Choi, Dongbo Min
In multi-task learning (MTL) for visual scene understanding, it is crucial to transfer useful information between multiple tasks with minimal interferences. In this paper, we propo…
Adaptive confidence thresholding for monocular depth estimation
Hyesong Choi, Hunsang Lee, Sunkyung Kim +4
Self-supervised monocular depth estimation has become an appealing solution to the lack of ground truth labels, but its reconstruction loss often produces over-smoothed results acr…