Seong Joon Oh

41 papers · 2015–2026 · 10 conferences · across top CS/AI conferences

Achievements

+14 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (10) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (10)

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (14) 👑 Triple Crown 🏆 Grand Slam 🧬 Topic Evolution 🔥 Unstoppable (9) 🚀 Conference Pioneer ⚡ Prolific Year (7) 📈 Trend Setter 🗃️ Keyword Collector (139) ❓ The Questioner (4) 💎 Century Club (39)

Conferences

ICCV (8) CVPR (7) ICLR (7) NIPS (7) ICML (5) ACL (3) AAAI (1) ECCV (1) EMNLP (1) NAACL (1)

Top co-authors

Sangdoo Yun (16) Sanghyuk Chun (10) Dongyoon Han (7) Junsuk Choe (7) Bernt Schiele (6) Martin Gubri (6) Mario Fritz (5) Byeongho Heo (4) Michael Kirchhof (3) Zeynep Akata (3)

Research topics

Privacy (3)

Keywords

weakly supervised learning (4) large language model (4) image classification (4) domain generalization (3) data augmentation (3) uncertainty quantification (3) representation learning (3) object localization (2) vision transformer (2) person recognition (2) contrastive learning (2) benchmark evaluation (2) image captioning (2) few-shot learning (2) object detection (2) transfer learning (2) semantic segmentation (2) image generation (2) domain adaptation (2) bayesian inference (2)

Papers

MASEval: Extending Multi-Agent Evaluation from Models to Systems ACL 2026 Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models ACL 2026 Do Deep Neural Network Solutions Form a Star Domain? ICLR 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025 Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 Decoupled Finetuning for Domain Generalizable Semantic Segmentation ICLR 2025 Does Data Scaling Lead to Visual Compositional Generalization? ICML 2025 Intermediate Layer Classifiers for OOD generalization ICLR 2025 TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024 Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks NIPS 2024 URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates NIPS 2023 ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets NIPS 2023 A Bayesian Approach To Analysing Training Data Attribution In Deep Learning NIPS 2023 Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs ICML 2023 Scratching Visual Transformer's Back with Uniform Attention ICCV 2023 Neglected Free Lunch - Learning Image Classifiers Using Annotation Byproducts ICCV 2023 ProPILE: Probing Privacy Leakage in Large Language Models NIPS 2023 Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data CVPR 2022 SelecMix: Debiased Learning by Contradicting-pair Sampling NIPS 2022 ALP: Data Augmentation Using Lexicalized PCFGs for Few-Shot Text Classification AAAI 2022 ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-Verified Image-Caption Associations for MS-COCO ECCV 2022 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective ICLR 2022 Dataset Condensation via Efficient Synthetic-Data Parameterization ICML 2022 Keep CALM and Improve Visual Feature Attribution ICCV 2021 AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights ICLR 2021 Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions NIPS 2021 Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized Labels CVPR 2021 Probabilistic Embeddings for Cross-Modal Retrieval CVPR 2021 Rethinking Spatial Dimensions of Vision Transformers ICCV 2021 Evaluating Weakly Supervised Object Localization Methods Right CVPR 2020 Learning De-biased Representations with Biased Representations ICML 2020 Reliable Fidelity and Diversity Metrics for Generative Models ICML 2020 CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features ICCV 2019 What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis ICCV 2019 Modeling Uncertainty with Hedged Instance Embeddings ICLR 2019 Natural and Effective Obfuscation by Head Inpainting CVPR 2018 Towards Reverse-Engineering Black-Box Neural Networks ICLR 2018 Exploiting Saliency for Object Segmentation From Image Level Labels CVPR 2017 Generating Descriptions With Grounded and Co-Referenced People CVPR 2017 Adversarial Image Perturbation for Privacy Protection -- A Game Theory Perspective ICCV 2017 Person Recognition in Personal Photo Collections ICCV 2015