no code implementations • 19 Mar 2024 • Mengzhou Li, Chuang Niu, Ge Wang, Maya R Amma, Krishna M Chapagain, Stefan Gabrielson, Andrew Li, Kevin Jonker, Niels de Ruiter, Jennifer A Clark, Phil Butler, Anthony Butler, Hengyong Yu
Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues.
no code implementations • 23 Dec 2023 • Su Jia, Andrew Li, R. Ravi, Nishant Oli, Paul Duff, Ian Anderson
We aim to minimize the loss due to not knowing the mean rewards, averaged over instances generated from a given prior distribution.
no code implementations • 23 Dec 2023 • Su Jia, Andrew Li, R. Ravi
Without monotonicity, the minimax regret is $\tilde O(n^{2/3})$ for the Lipschitz demand family and $\tilde O(n^{1/2})$ for a general class of parametric demand models.
no code implementations • 7 Aug 2023 • Jordan Dotzel, Gang Wu, Andrew Li, Muhammad Umar, Yun Ni, Mohamed S. Abdelfattah, Zhiru Zhang, Liqun Cheng, Martin G. Dixon, Norman P. Jouppi, Quoc V. Le, Sheng Li
With integer models, we increase the accuracy of ResNet-18 on ImageNet by 1. 31% and ResNet-50 by 0. 90% with equivalent model cost over previous methods.
1 code implementation • 29 Mar 2023 • Jaehwan Jeong, Katherine Tian, Andrew Li, Sina Hartung, Fardad Behzadi, Juan Calle, David Osayande, Michael Pohlen, Subathra Adithan, Pranav Rajpurkar
In this work, we propose Contrastive X-Ray REport Match (X-REM), a novel retrieval-based radiology report generation module that uses an image-text matching score to measure the similarity of a chest X-ray image and radiology report for report retrieval.
no code implementations • ICCV 2023 • Cheng Fu, Hanxian Huang, Zixuan Jiang, Yun Ni, Lifeng Nai, Gang Wu, Liqun Cheng, Yanqi Zhou, Sheng Li, Andrew Li, Jishen Zhao
One promising way to accelerate transformer training is to reuse small pretrained models to initialize the transformer, as their existing representation power facilitates faster model convergence.
no code implementations • NeurIPS 2021 • Kyra Gan, Su Jia, Andrew Li
In the problem of active sequential hypothesis testing (ASHT), a learner seeks to identify the true hypothesis from among a known set of hypotheses.
1 code implementation • 13 Feb 2021 • Pashootan Vaezipoor, Andrew Li, Rodrigo Toro Icarte, Sheila Mcilraith
We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments.
no code implementations • CVPR 2021 • Sheng Li, Mingxing Tan, Ruoming Pang, Andrew Li, Liqun Cheng, Quoc Le, Norman P. Jouppi
On top of our DC accelerator optimized neural architecture search space, we further propose a latency-aware compound scaling (LACS), the first multi-objective compound scaling method optimizing both accuracy and latency.
4 code implementations • 16 Sep 2018 • Michael Danielczuk, Matthew Matl, Saurabh Gupta, Andrew Li, Andrew Lee, Jeffrey Mahler, Ken Goldberg
We train a variant of Mask R-CNN with domain randomization on the generated dataset to perform category-agnostic instance segmentation without any hand-labeled data and we evaluate the trained network, which we refer to as Synthetic Depth (SD) Mask R-CNN, on a set of real, high-resolution depth images of challenging, densely-cluttered bins containing objects with highly-varied geometry.
Ranked #1 on Unseen Object Instance Segmentation on WISDOM