James Duncan

5 papers · 2020–2023 · 2 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

NeurIPS (4) ICML (1)

Top co-authors

Juntang Zhuang (3) Nicha Dvornek (3) Sekhar C Tatikonda (2) Xenophon Papademetris (2) Fenglin Liu (2) Lawrence Staib (2) Tommy Tang (2) Yifan Ding (2) Chenyu You (2) sekhar tatikonda (1)

Research topics

Machine Learning (5) Optimization & Theory (3) Computer Vision (2) Deep Learning (2) Architectures (2) Domain-Specific (2) Learning Types · Machine Learning (2) Artificial Intelligence (1) Analysis (1) Core AI (1) Learning Types · Deep Learning (1) Processing (1)

Keywords

medical image segmentation (2) contrastive learning (1) stochastic gradient descent (1) semantic segmentation (1) semi-supervised learning (1) adversarial training (1) gradient estimation (1) variance reduction (1) convergence rate (1) neural ordinary differential equation (1) adaptive step size (1) adjoint method (1) multi-scale representation (1) adaptive gradient (1) exponential moving average (1) adaptive optimizer (1) asynchronous update (1) stochastic non-convex optimization (1) image classification (1) momentum centering (1)

Papers

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective NeurIPS 2023 Class-Aware Adversarial Transformers for Medical Image Segmentation NeurIPS 2022 Momentum Centering and Asynchronous Update for Adaptive Gradient Methods NeurIPS 2021 AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients NeurIPS 2020 Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE ICML 2020