Publications
2024
- Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
- SeiT++: Masked Token Modeling Improves Storage-efficient Training
- Memory-Efficient Fine-Tuning for Quantized Diffusion Model
- Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
- Locally Conditioned GANs: Self-supervised Local Patch Representation Learning for Conditional Generation
D Kim, H Shim
IEEE Access, 2024 - Preventing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval
- Adapting Low-Dose CT Denoisers for Texture Preservation using Zero-Shot Local Noise-level Matching
- Weakly Supervised Semantic Segmentation for Driving Scenes
- Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
- Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
- Local Expert Diffusion Models for Efficient Training in Denoising Diffusion Probabilistic Models
2023
- Saliency as Pseudo-pixel Supervision for Weakly and Semi-supervised Semantic Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2023.
- Entropy Regularization for Weakly Supervised Object Localization
- Your Lottery Ticket is Damaged: Towards All-Alive Pruning for Extremely Sparse Networks
- Utilization of an Attentive Map to Preserve Anatomical Features for Training Convolutional Neural Network based Low-dose CT Denoiser.
M Han, H Shim, J Baek, Medical Physics (MP), 2023 - CoMix: Collaborative Filtering with Mixup for Implicit Datasets
J Moon, Y Jeong, D-K Chae, J Choi, H Shim, J Lee, Information Sciences (IS), 2023. - Few-shoot Font Generation with Weakly Supervised Localized Representations
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2023.
- F2RPC: Fake to Real Portrait Control from a Virtual Character
IEEE Access, 2023.
- HybridMatch: Semi-supervised Facial Landmark Detection via Hybrid Heatmap Representations
S Kang*, M Lee*, M Kim, H Shim (* indicates an equal contribution)
IEEE Access, 2023.
2022
- Long-tail Mixup for Extreme Multi-label Classification
ACM International Conference on Information & Knowledge Management (CIKM), 2022.
- A streak artifact reduction algorithm in sparse-view CT using a self-supervised neural representation
Medical Physics (MP), 2022. (Editor's Choice)
- Perceptual CT Loss: Implementing CT Image Specific Perceptual Loss for CNN-Based Low-Dose CT Denoiser
M Han, H Shim, J Baek
IEEE Access, 2022. (Accepted) - Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets
J Choe*, S-J Oh*, S Chun, S Lee, Z Akata,, H Shim
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2022. (Accepted) - Knowledge distillation meets recommendation: collaborative distillation for top-N recommendation
J-W Lee, M Choi, S Lee, H Shim, J Lee
Knowledge and Information Systems (KIS), 2022. - Logit Mixing Training for More Reliable and Accurate Prediction
International Joint Conference on Artificial Intelligence (IJCAI), 2022
- Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
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 Thresholds
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
- Learning from Better Supervision: Self-distillation for Learning with Noisy Labels
- Two-phase Learning-based 3D Deblurring Method for Digital Breast Tomosynthesis Images
Y Choi, M Han, H Jang, H Shim, J Baek
Plos One, 2022. (Accepted) - S-Walk: Accurate and Scalable Session-based Recommendation with Random Walks
2021
- Knowledge Distillation Meets Recommendation: Collaborative Distillation for Top-N Recommendation
Knowledge and Information Systems (KAIS), 2021.
- Distilling from Professors: Enhancing the Knowledge Distillation of Teachers
Information Sciences (IS), 2021.
- Low Dose CT Denoising via Convolutional Neural Network with an Observer Loss Function
Medical Physics (MP), 2021.
- Rethinking the Truly Unsupervised Image-to-Image Translation
International Conference on Computer Vision (ICCV), 2021.
- Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
International Conference on Computer Vision (ICCV), 2021.
Weakly-Supervised Progressive Denoising with Unpaired CT Images
Region-based Dropout with Attention Prior for Weakly Supervised Object Localization
Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation
Session-aware Linear Item-Item Models for Session-based Recommendation
Few-shot Font Generation with Localized Style Representations and Factorization
2020
Attention-based Dropout Layer for Weakly Supervised Single Object Localization and Semantic Segmentation
Evaluating Weakly Supervised Object Localization Methods Right
Discriminator Feature-based Inference by Recycling the Discriminator of GANs
Diversity Regularized Autoencoders for Text Generation
A convolutional neural network‐based model observer for breast CT images
2019
- Collaborative Distillation for Top-N Recommendation
- CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
- A performance comparison of convolutional neural network‐based image denoising methods:
- Attention-based Dropout Layer for Weakly Supervised Object Localization
- An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
Semantic-Aware Neural Style Transfer
- Dual Neural Personalized Ranking