Ph.D. Dissertations - Trevor Darrell

Efficient and Scalable Neural Architectures for Visual Recognition
Zhuang Liu [2022]

Learning to Generalize in Dynamic Environments
Dequan Wang [2022]

Multi-task Policy Learning with Minimal Human Supervision
Parsa Mahmoudieh [2022]

Adaptive Prediction and Planning for Safe and Effective Autonomous Vehicles
Vijay Govindarajan [2021]

Learning Predictive Models for Efficient Policy Learning
Huazhe Xu [2021]

Visual Content Creation by Generative Adversarial Networks
Samaneh Azadi [2021]

Adapting Across Domains by Aligning Representations and Images
Eric Tzeng [2020]

Compositionality and Modularity for Robot Learning
Coline Devin [2020]

Structured Models for Vision-and-Language Reasoning
Ronghang Hu [2020]

The Design of Dynamic Neural Networks for Efficient Learning and Inference
Xin Wang [2020]

End to End Learning in Autonomous Driving Systems
Yang Gao [2019]

Learning to Generalize via Self-Supervised Prediction
Deepak Pathak [2019]

Local and Adaptive Image-to-Image Learning and Inference
Evan Shelhamer [2019]

Visual Understanding through Natural Language
Lisa Hendricks [2019]

Transferrable Representations for Visual Recognition
Jeffrey Donahue [2017]

Adaptive Learning Algorithms for Transferable Visual Recognition
Judy Hoffman [2016]

Understanding and Designing Convolutional Networks for Local Recognition Problems
Jonathan Long [2016]

Visual Representations for Fine-grained Categorization
Ning Zhang [2015]

Anytime Recognition of Objects and Scenes
Sergey Karayev [2014]

Learning Semantic Image Representations at a Large Scale
Yangqing Jia [2014]

Learning with Parsimony for Large Scale Object Detection and Discovery
Hyun Oh Song [2014]

Finding Lost Children
Ashley Michelle Eden [2010]