Publications

Conference Publication (International)

• [C11] CLDA: Collaborative Learning for Unsupervised Enhanced Domain Adaptation

  Minhee Cho, Hyesong Choi, Hayeon Jo, and Dongbo Min · IEEE ICASSP, 2026

• [C10] RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo

  Jueun Ko, Hyewon Park, Hyesong Choi, and Dongbo Min · NeurIPS, 2025

• [C9] TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning

  Seungmin Baek, Soyul Lee, Hayeon Jo, Hyesong Choi, and Dongbo Min · IEEE CVPR, 2025

• [C8] A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations

  Wonil Song, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min · NeurIPS, 2024

• [C7] Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training

  Hyesong Choi, Hyejin Park, Kwang Moo Yi, Sungmin Cha, and Dongbo Min · ECCV, 2024

• [C6] Emerging Property of Masked TOken for Effective Pre-training

  Hyesong Choi, Hunsang Lee, Seyoung Joung, Hyejin Park, Jiyeong Kim, and Dongbo Min · ECCV, 2024

• [C5] Environment Agnostic Representation for Visual Reinforcement Learning

  Hyesong Choi, Hunsang Lee, Seongwon Jeong, and Dongbo Min · IEEE ICCV, 2023

• [C4] Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning

  Hyesong Choi, Hunsang Lee, Wonil Song, Sangryul Jeon, Kwanghoon Sohn, and Dongbo Min · IEEE CVPR, 2023

• [C3] KNN Local Attention for Image Restoration

  Hunsang Lee, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min · IEEE CVPR, 2022

• [C2] Sequential Cross Attention Based Multi-Task Learning

  Sunkyung Kim, Hyesong Choi, and Dongbo Min · IEEE ICIP, 2022

• [C1] Adaptive Confidence Thresholding for Monocular Depth Estimation

  Hyesong Choi, Hunsang Lee, Sunok Kim, Seungryoung Kim, and Dongbo Min · IEEE ICCV, 2021

Journal Publication (International)

• [J5] UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching

  Soomin Kim, Hyesong Choi, Jihye Ahn, and Dongbo Min · IEEE ACCESS (IF=3.476), 2025

• [J4] Global Structural Knowledge Distillation for Semantic Segmentation

  Hyejin Park, Keonhee Ahn, Hyesong Choi, and Dongbo Min · IEEE ACCESS (IF=3.476), 2025

• [J3] MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling

  Jihye Ahn, Hyesong Choi, Sommin Kim, and Dongbo Min · IEEE ACCESS (IF=3.476), 2025

• [J2] Cross-Scale KNN Image Transformer for Image Restoration

  Hunsang Lee, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min · IEEE ACCESS (IF=3.476), 2023

• [J1] Learning Disentangled Skills for Hierarchical Reinforcement Learning through Trajectory Autoencoder with Weak Labels

  Wonil Song, Sangryul Jeon, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min · Expert Systems with Applications (ESWA) (IF=7.5), 2023

Preprint

• [P4] What Does the Caption Really Say? Counterfactual Phrase Intervention for Compositional Data Selection in Vision-Language Pretraining

  Hyejin Go, Semi Lee, and Hyesong Choi · arXiv preprint, 2026

• [P3] AdaMerge: Salience-Aware Adaptive Token Merging for Training-Free Acceleration of Vision Transformers

  Semi Lee, Hyejin Go, Hyesong Choi
  under review, 2026

• [P2] When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection

  Jihyeon Kim, Sohee Kim, Soosan Lee, Souhwan Jung, James Matthew Rehg, Hyesong Choi
  under review, 2026

• [P1] The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP

  Kahyeon Nam, Hyesong Choi · arXiv preprint, 2026