Skip to content
conftrace_

Karsten Roth

23 papers · 2019–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (37) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🀝 Dynamic Duo (15)
🀝 Dynamic Duo (15) πŸ—ƒοΈ Keyword Collector (87) πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner (2) ⚑ Prolific Year Β· Productive πŸ“ˆ Trend Setter πŸ’Ž Century Club Β· Bronze

Venues

CVPR (6) ICLR (5) ICML (4) ECCV (3) NeurIPS (3) ICCV (2)

Top co-authors

Zeynep Akata (15) Bjorn Ommer (6) Oriol Vinyals (5) Timo Milbich (5) Matthias Bethge (3) Joseph Paul Cohen (3) Samarth Sinha (3) Marzyeh Ghassemi (3) A. Sophia Koepke (2) Shyamgopal Karthik (2)

Research topics

Machine Learning (19) Core Methods (12) Deep Learning (9) Artificial Intelligence (8) Application Areas (8) Learning Types Β· Machine Learning (6) Core AI (5) Learning Paradigms (5) Learning Types Β· Deep Learning (4) Optimization & Theory (3) Techniques (3) Computer Vision (2) Models (2) Natural Language Processing (1) Reinforcement Learning (1)

Keywords

deep metric learning (6) embedding space (3) zero-shot learning (3) vision-language model (3) contrastive learning (3) representation learning (3) embedding learning (3) transfer learning (2) few-shot learning (2) knowledge distillation (2) metric learning (2) visual similarity (2) disentangled representation (2) multimodal learning (2) distribution shift (2) foundation model (2) image retrieval (2) anomaly detection (1) continual learning (1) image generation (1)

Papers

Context-Aware Multimodal Pretraining CVPR 2025 Disentangled Representation Learning with the Gromov-Monge Gap ICLR 2025 How to Merge Your Multimodal Models Over Time? CVPR 2025 WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs ICML 2025 A Practitioner's Guide to Real-World Continual Multimodal Pretraining NeurIPS 2024 ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections ICML 2024 Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model ICLR 2024 Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models ECCV 2024 ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization NeurIPS 2024 Vision-by-Language for Training-Free Compositional Image Retrieval ICLR 2024 Disentanglement of Correlated Factors via Hausdorff Factorized Support ICLR 2023 Waffling Around for Performance: Visual Classification with Random Words and Broad Concepts ICCV 2023 A Non-Isotropic Probabilistic Take On Proxy-Based Deep Metric Learning ECCV 2022 Integrating Language Guidance Into Vision-Based Deep Metric Learning CVPR 2022 Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning ICLR 2022 Non-Isotropy Regularization for Proxy-Based Deep Metric Learning CVPR 2022 Towards Total Recall in Industrial Anomaly Detection CVPR 2022 Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning NeurIPS 2021 Simultaneous Similarity-based Self-Distillation for Deep Metric Learning ICML 2021 DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning ECCV 2020 PADS: Policy-Adapted Sampling for Visual Similarity Learning CVPR 2020 Revisiting Training Strategies and Generalization Performance in Deep Metric Learning ICML 2020 MIC: Mining Interclass Characteristics for Improved Metric Learning ICCV 2019