Sanghyuk Chun

An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval ICCV 2025 Probabilistic Language-Image Pre-Training ICLR 2025 Read, Watch and Scream! Sound Generation from Text and Video AAAI 2025 Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study NeurIPS 2024 HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts ECCV 2024 Improved Probabilistic Image-Text Representations ICLR 2024 Language-only Training of Zero-shot Composed Image Retrieval CVPR 2024 Learning with Unmasked Tokens Drives Stronger Vision Learners ECCV 2024 Similarity of Neural Architectures using Adversarial Attack Transferability ECCV 2024 Toward Interactive Regional Understanding in Vision-Large Language Models NAACL 2024 What does automatic differentiation compute for neural networks? ICLR 2024 Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization ICLR 2023 SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage ICCV 2023 A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective NeurIPS 2022 Dataset Condensation with Contrastive Signals ICML 2022 Domain Generalization by Mutual-Information Regularization with Pre-trained Models ECCV 2022 ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-Verified Image-Caption Associations for MS-COCO ECCV 2022 Learning Fair Classifiers With Partially Annotated Group Labels CVPR 2022 ViDT: An Efficient and Effective Fully Transformer-based Object Detector ICLR 2022 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective ICLR 2022 AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights ICLR 2021 Few-shot Font Generation with Localized Style Representations and Factorization AAAI 2021 Multiple Heads Are Better Than One: Few-Shot Font Generation With Multiple Localized Experts ICCV 2021 Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions NeurIPS 2021 Probabilistic Embeddings for Cross-Modal Retrieval CVPR 2021 Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels CVPR 2021 Rethinking Spatial Dimensions of Vision Transformers ICCV 2021 SWAD: Domain Generalization by Seeking Flat Minima NeurIPS 2021 Evaluating Weakly Supervised Object Localization Methods Right CVPR 2020 Few-shot Compositional Font Generation with Dual Memory ECCV 2020 Learning De-biased Representations with Biased Representations ICML 2020 CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features ICCV 2019 Photorealistic Style Transfer via Wavelet Transforms ICCV 2019