Search Results - "Dey, Debadeepta"

Data-driven planning via imitation learning by Choudhury, Sanjiban, Bhardwaj, Mohak, Arora, Sankalp, Kapoor, Ashish, Ranade, Gireeja, Scherer, Sebastian, Dey, Debadeepta

“…Robot planning is the process of selecting a sequence of actions that optimize for a task=specific objective. For instance, the objective for a navigation task…”
Get full text

Submodular Trajectory Optimization for Aerial 3D Scanning by Roberts, Mike, Shah, Shital, Dey, Debadeepta, Truong, Anh, Sinha, Sudipta, Kapoor, Ashish, Hanrahan, Pat, Joshi, Neel

“…Drones equipped with cameras are emerging as a powerful tool for large-scale aerial 3D scanning, but existing automatic flight planners do not exploit all…”
Get full text

Classification of plant structures from uncalibrated image sequences by Dey, D., Mummert, L., Sukthankar, R.

“…This paper demonstrates the feasibility of recovering fine-scale plant structure in 3D point clouds by leveraging recent advances in structure from motion and…”
Get full text

Learning monocular reactive UAV control in cluttered natural environments by Ross, Stephane, Melik-Barkhudarov, Narek, Shankar, Kumar Shaurya, Wendel, Andreas, Dey, Debadeepta, Bagnell, J. Andrew, Hebert, Martial

“…Autonomous navigation for large Unmanned Aerial Vehicles (UAVs) is fairly straight-forward, as expensive sensors and monitoring devices can be employed. In…”
Get full text

Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention by Nguyen, Khanh, Dey, Debadeepta, Brockett, Chris, Dolan, Bill

“…We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via…”
Get full text

Blind Spot Detection for Safe Sim-to-Real Transfer by Ramakrishnan, Ramya, Kamar, Ece, Dey, Debadeepta, Horvitz, Eric, Shah, Julie

“…Agents trained in simulation may make errors when performing actions in the real world due to mismatches between training and execution environments. These…”
Get full text

A cascaded method to detect aircraft in video imagery by Dey, Debadeepta, Geyer, Christopher, Singh, Sanjiv, Digioia, Matthew

“…Unmanned Aerial Vehicles (UAVs) have played vital roles recently in both military and non-military applications. One of the reasons UAVs today are unable to…”
Get full text

Spoken language interaction with robots: Recommendations for future research by Marge, Matthew, Espy-Wilson, Carol, Ward, Nigel G., Alwan, Abeer, Artzi, Yoav, Bansal, Mohit, Blankenship, Gil, Chai, Joyce, Daumé, Hal, Dey, Debadeepta, Harper, Mary, Howard, Thomas, Kennington, Casey, Kruijff-Korbayová, Ivana, Manocha, Dinesh, Matuszek, Cynthia, Mead, Ross, Mooney, Raymond, Moore, Roger K., Ostendorf, Mari, Pon-Barry, Heather, Rudnicky, Alexander I., Scheutz, Matthias, Amant, Robert St, Sun, Tong, Tellex, Stefanie, Traum, David, Yu, Zhou

“…With robotics rapidly advancing, more effective human–robot interaction is increasingly needed to realize the full potential of robots for society. While…”
Get full text

Flight Dynamics-Based Recovery of a UAV Trajectory Using Ground Cameras by Rozantsev, Artem, Sinha, Sudipta N., Dey, Debadeepta, Fua, Pascal

“…We propose a new method to estimate the 6-dof trajectory of a flying object such as a quadrotor UAV within a 3D airspace monitored using multiple fixed ground…”
Get full text

Predicting Multiple Structured Visual Interpretations by Dey, Debadeepta, Ramakrishna, Varun, Hebert, Martial, Bagnell, J. Andrew

“…We present a simple approach for producing a small number of structured visual outputs which have high recall, for a variety of tasks including monocular pose…”
Get full text

FEAR: A Simple Lightweight Method to Rank Architectures by Dey, Debadeepta, Shah, Shital, Bubeck, Sebastien

“…The fundamental problem in Neural Architecture Search (NAS) is to efficiently find high-performing architectures from a given search space. We propose a simple…”
Get full text

What Makes Convolutional Models Great on Long Sequence Modeling? by Li, Yuhong, Cai, Tianle, Zhang, Yi, Chen, Deming, Dey, Debadeepta

“…Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle…”
Get full text

Learning to gather information via imitation by Choudhury, Sanjiban, Kapoor, Ashish, Ranade, Gireeja, Dey, Debadeepta

“…The budgeted information gathering problem - where a robot with a fixed fuel budget is required to maximize the amount of information gathered from the world -…”
Get full text

Neural Architecture Search: Insights from 1000 Papers by White, Colin, Safari, Mahmoud, Sukthanker, Rhea, Ru, Binxin, Elsken, Thomas, Zela, Arber, Dey, Debadeepta, Hutter, Frank

“…In the past decade, advances in deep learning have resulted in breakthroughs in a variety of areas, including computer vision, natural language understanding,…”
Get full text

One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning by Girish, Sharath, Dey, Debadeepta, Joshi, Neel, Vineet, Vibhav, Shah, Shital, Mendes, Caio Cesar Teodoro, Shrivastava, Abhinav, Song, Yale

“…The current literature on self-supervised learning (SSL) focuses on developing learning objectives to train neural networks more effectively on unlabeled data…”
Get full text

AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models by Xu, Dongkuan, Mukherjee, Subhabrata, Liu, Xiaodong, Dey, Debadeepta, Wang, Wenhui, Zhang, Xiang, Awadallah, Ahmed Hassan, Gao, Jianfeng

“…Knowledge distillation (KD) methods compress large models into smaller students with manually-designed student architectures given pre-specified computational…”
Get full text

Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints by Jawahar, Ganesh, Mukherjee, Subhabrata, Dey, Debadeepta, Abdul-Mageed, Muhammad, Lakshmanan, Laks V. S, Mendes, Caio Cesar Teodoro, de Rosa, Gustavo Henrique, Shah, Shital

“…Autocomplete is a task where the user inputs a piece of text, termed prompt, which is conditioned by the model to generate semantically coherent continuation…”
Get full text

Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention by Nguyen, Khanh, Dey, Debadeepta, Brockett, Chris, Dolan, Bill

“…We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via…”
Get full text

Quality and Relevance Metrics for Selection of Multimodal Pretraining Data by Rao, Roshan, Rao, Sudha, Nouri, Elnaz, Dey, Debadeepta, Celikyilmaz, Asli, Dolan, Bill

“…Self-supervised pretraining has become a strong force in both language and vision tasks. Current efforts to improve the effects of pretraining focus on…”
Get full text

Reparameterized Variational Divergence Minimization for Stable Imitation by Arumugam, Dilip, Dey, Debadeepta, Agarwal, Alekh, Celikyilmaz, Asli, Nouri, Elnaz, Dolan, Bill

“…While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from…”
Get full text