3D-Aware Vision-Language Models Fine-Tuning with Geometric DistillationSeonho Lee*, Jiho Choi*, Inha Kang, Jiwook Kim, Junsung Park, Hyunjung ShimEMNLP 2025 Findings Scribble-Guided Diffusion for Training-free Text-to-Image GenerationSeonho Lee*, Jiho Choi*, Seohyun Lim, Jiwook Kim, Hyunjung ShimICIP 2025 I0T: Embedding Standardization Method Towards Zero Modality Gap Na Min An*, Eunki. Kim*, James Thorne, Hyunjung ShimACL 2025 Outstanding paper Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part SegmentationJiho Choi*, Seonho Lee*, Minhyun Lee, Seungho Lee, Hyunjung ShimCVPR 2025 Classifier-guided CLIP Distillation for Unsupervised Multi-label ClassificationDongseob Kim, Hyunjung ShimCVPR 2025 No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse WeatherJunsung Park, Hwijeong Lee, Inha Kang, Hyunjung ShimCVPR 2025 DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsHyogon Ryu, NaHyeon Park, Hyunjung ShimICLR 2025 DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity PreservationJiwook Kim*, Seonho Lee*, Jaeyo Shin, Jiho Choi, Hyunjung ShimICLR 2025 Label-Augmented Dataset DistillationSeoungyoon Kang*, Youngsun Lim*, Hyunjung Shim (* indicates an equal contribution)WACV 2025 Oral Evaluating Image Hallucination in Text-to-Image Generation with Question-AnsweringY Lim*, H Choi*, H Shim (* indicates an equal contribution)AAAI 2025 Oral Understanding Multi-Granularity for Open-Vocabulary Part SegmentationJiho Choi*, Seonho Lee*, Seungho Lee, Minhyun Lee, Hyunjung Shim (* indicates an equal contribution)NeurIPS 2024 Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse WeatherJunsung Park, Kyungmin Kim, Hyunjung ShimECCV 2024 Oral SeiT++: Masked Token Modeling Improves Storage-efficient Training Minhyun Lee*, Song Park*, Byeongho Heo, Dongyoon Han, Hyunjung Shim (* indicates an equal contribution)ECCV 2024 Memory-Efficient Fine-Tuning for Quantized Diffusion Model Hyogon Ryu, Seohyun Lim, Hyunjung ShimECCV 2024 Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic SegmentationSeungho Lee, Hwijeong Lee, Hyunjung ShimIROS 2024 Oral Preventing Image Hallucination in Text-to-Image Generation through Factual Image RetrievalYoungsun Lim, Hyunjung ShimIJCAI Workshop on Trustworthy Interactive Decision-Making with Foundation Models 2024 Weakly Supervised Semantic Segmentation for Driving ScenesDongseob Kim*, Seungho Lee*, Junsuk Choe, Hyunjung Shim(* indicates an equal contribution)AAAI 2024 Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect LabelsSeungho Lee*, Seoungyoon Kang*, Hyunjung Shim(* indicates an equal contribution) The 38th Annual AAAI Conference on Artificial Intelligence Workshops on The 3rd Edge Intelligence Workshop on Large Language and Vision Models(AAAIW), 2024 Precision matters: Precision-aware ensemble for weakly supervised semantic segmentationJunsung Park, Hyunjung Shim The 38th Annual AAAI Conference on Artificial Intelligence Workshops on The 3rd Edge Intelligence Workshop on Large Language and Vision Models(AAAIW), 2024 Local Expert Diffusion Models for Efficient Training in Denoising Diffusion Probabilistic ModelsSeoungyoon Kang*, Yunji Jung*, Hyunjung Shim(* indicates an equal contribution) The 38th Annual AAAI Conference on Artificial Intelligence Workshops on Sustainable AI(AAAIW), 2024 TADA: Timestep-Aware Data Augmentation for Diffusion ModelsNaHyeon Park*, Kunhee Kim*, Song Park, Jung-Woo Ha, Hyunjung Shim Neural Information Processing Systems Workshop on Diffusion Models(NeurIPSW), 2023 F2RPC: Fake to Real Portrait Control from a Virtual CharacterS Kang, M Kim, H Shim IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops(VRW), 2023 Long-tail Mixup for Extreme Multi-label Classification S Han, E Choi, C Lim, J Lee, H Shim, J Lee ACM International Conference on Information & Knowledge Management(CIKM), 2022 Logit Mixing Training for More Reliable and Accurate PredictionD Bang*, K Baek*, J Kim, Y Jeon, JH Kim, J kim, J Lee, H Shim (* indicates an equal contribution) International Joint Conference on Artificial Intelligence(IJCAI), 2022 Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic DataK Baek, H Shim IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against ThresholdsM Lee*, D Kim*, H Shim (* indicates an equal contribution) IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Learning from Better Supervision: Self-distillation for Learning with Noisy LabelsKBaek*, S Lee*, H Shim (* indicates an equal contribution) International Conference on Pattern Recognition (ICPR), 2022 S-Walk: Accurate and Scalable Session-based Recommendation with Random WalksM Choi, J Kim, J Lee, H Shim, J Lee International Conference on Web Search and Data Mining (WSDM), 2022. (Accepted) Rethinking the Truly Unsupervised Image-to-Image TranslationK Baek, Y Choi, Y Uh, J Yoo, H Shim International Conference on Computer Vision (ICCV), 2021. Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized ExpertsS Park, S Chun, J Cha, B Lee, H Shim International Conference on Computer Vision (ICCV), 2021.
MGGAN: Solving Mode Collapse using Manifold-guided Training
D Bang, H Shim International Conference on Computer Vision Workshop on More Exploration, Less Exploitation (MELEX) (ICCVW), 2021. Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation S Lee*, M Lee*, J Lee, H Shim (* indicates an equal contribution) IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Session-aware Linear Item-Item Models for Session-based Recommendation M Choi, J Kim, J Lee, H Shim and J Lee The Web Conference (WWW), 2021 Few-shot Font Generation with Localized Style Representations and Factorization S Park*, S Chun*, J Cha, B Lee, H ShimAssociation for the Advancement of Artificial Intelligence (AAAI), 2021IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2021 Evaluating Weakly Supervised Object Localization Methods Right J Choe*, S J Oh*, S Lee, S Chun, Z Akata, H ShimIEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Diversity Regularized Autoencoders for Text Generation H Ko, J Lee, J Kim, J Lee, HShim35th ACM/SIGAPP Symposium on Applied Computing (SAC), 2020 PsyNet: Self-supervised Object Localization using Point Symmetric Transformation K Baek*, M H Lee*, H Shim (* indicates an equal contribution)Association for the Advancement of Artificial Intelligence (AAAI), 2020 Collaborative Distillation for Top-N Recommendation J Lee, M Choi, J Lee, and H ShimIEEE International Conference on Data Mining (ICDM), Oral presentation, 2019 CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features S Yun, D Han, S J Oh, S Chun, J Choe, Y Yoo.International Conference on Computer Vision (ICCV), Oral presentation, 2019 Attention-based Dropout Layer for Weakly Supervised Object Localization J Choe, H ShimIEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral presentation, 2019 An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods S Chun, S J Oh, S Yun, D Han, J Choe, Y Yoo.International Conference on Machine Learning Workshop (ICMLW), 2019 Dual Neural Personalized Ranking S Kim, J Lee, H ShimThe Web Conference 2019 (WWW), Oral presentation, 2019 Depth Reconstruction of Translucent Objects from a Single Time-of-Flight Camera using Deep Residual Networks S Song, H Shim Asian Conference on Computer Vision (ACCV), 2018 Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously K Baek, D Bang, H Shim Asian Conference on Computer Vision (ACCV), Oral presentation, 2018 Resembled Generative Adversarial Networks: Two Domains with Similar Attributes D Bang, H Shim British Machine Vision Conference (BMVC), 2018 Improved Training of Generative Adversarial Networks using Representative FeaturesD Bang, H Shim IEEE International Conference on Machine Learning (ICML), 2018 Face Generation for Low-shot Learning using Generative Adversarial Networks J Choe*, S Park*, K Kim*, J Park*, D Kim*, H Shim IEEE International Conference on Computer Vision Workshop (ICCVW), 2017 Data-driven Approach to Aesthetic Enhancement J Choi, S Koh, J Kwack, Y Kwon, H Shim Electronic Imaging, 2016 Developing a Visual Stopping Criterion for Image Mosaicing using Invariant Color Histograms A Elibol, H Shim Pacific Rim Conference on Multimedia, 2015 Inverse Lighting for Non-homogeneous Objects from Color and Depth Image using Wavelet Representation J Choe, H Shim IS&T/SPIE Electronic Imaging, 2015 Depth Image Enhancement using Perceptual Texture PriorsD Bang, H Shim IS&T/SPIE Electronic Imaging, 2015 3D Motion Artifact Compensation in CT Image with Depth CameraY Ko, J Baek, H Shim IS&T/SPIE Electronic Imaging, 2015 Estimating All Frequency Lighting using a Color/Depth Image Hyunjung ShimIEEE International Conference on Image Processing (ICIP), 2012 An Example-based Face RelightingH Shim, T Chen Proceedings of SPIE, 2012 Automatic Color Realism Enhancement for Virtual RealityH Shim, S Lee IEEE Virtual Reality (IEEE VR), 2012 Light Weight Multiview Capturing H Shim, T Chen, S Lee, JD Kim, C Kim IEEE Consumer Communications and Networking Conference (CCNC), 2012 A Probabilistic Approach to Realistic Face Synthesis H Shim, I Ha, T Rhee, JD Kim, C KimIEEE International Conference on Image Processing (ICIP), 2010 Adaptive Environment Map for Relighting: using Cameras and Projected Light H Shim, T ChenIEEE Computer Vision and Pattern Recognition Workshop (CVPRW), 2006 A Statistical Framework for Image-based Relighting H Shim, T ChenIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2005 Efficient Representation of Lighting Patterns for Image-based Relighting H Shim, T ChenProc. Picture coding symposium (PCS), 2004