1 code implementation • 22 Nov 2023 • McKell Woodland, Mais Al Taie, Jessica Albuquerque Marques Silva, Mohamed Eltaher, Frank Mohn, Alexander Shieh, Austin Castelo, Suprateek Kundu, Joshua P. Yung, Ankit B. Patel, Kristy K. Brock
A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images.
Ranked #1 on Medical Image Generation on SLIVER07
1 code implementation • 7 Aug 2023 • McKell Woodland, Nihil Patel, Mais Al Taie, Joshua P. Yung, Tucker J. Netherton, Ankit B. Patel, Kristy K. Brock
Clinically deployed segmentation models are known to fail on data outside of their training distribution.
no code implementations • 14 Jul 2023 • Ryan Pyle, Sebastian Musslick, Jonathan D. Cohen, Ankit B. Patel
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task.
no code implementations • 10 Jul 2023 • McKell Woodland, John Wood, Caleb O'Connor, Ankit B. Patel, Kristy K. Brock
Our OOD test data consisted of CT images of the brain, head and neck, lung, cervix, and abnormal livers.
no code implementations • 7 Feb 2023 • Hao Liang, Josue Ortega Caro, Vikram Maheshri, Ankit B. Patel, Guha Balakrishnan
Our framework is experimental, in that we train several versions of a network with an intervention to a specific hyperparameter, and measure the resulting causal effect of this choice on performance bias when a particular out-of-distribution image perturbation is applied.
no code implementations • 7 Oct 2022 • McKell Woodland, John Wood, Brian M. Anderson, Suprateek Kundu, Ethan Lin, Eugene Koay, Bruno Odisio, Caroline Chung, Hyunseon Christine Kang, Aradhana M. Venkatesan, Sireesha Yedururi, Brian De, Yuan-Mao Lin, Ankit B. Patel, Kristy K. Brock
Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images.
Ranked #1 on Medical Image Generation on ACDC
no code implementations • 8 Sep 2022 • Bishal Lamichhane, Nidal Moukaddam, Ankit B. Patel, Ashutosh Sabharwal
Psychomotor retardation in depression has been associated with speech timing changes from dyadic clinical interviews.
1 code implementation • 16 Mar 2022 • Nikos Karantzas, Emma Besier, Josue Ortega Caro, Xaq Pitkow, Andreas S. Tolias, Ankit B. Patel, Fabio Anselmi
Our results also indicate that the essential frequencies in question are effectively the ones used to achieve generalization in the first place.
1 code implementation • NeurIPS 2020 • Weili Nie, Zhiding Yu, Lei Mao, Ankit B. Patel, Yuke Zhu, Animashree Anandkumar
Inspired by the original one hundred BPs, we propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning.
no code implementations • 12 Jun 2020 • Weili Nie, Zichao Wang, Ankit B. Patel, Richard G. Baraniuk
Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning.
no code implementations • ICML 2020 • Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath, Anjul Patney, Ankit B. Patel, Anima Anandkumar
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation.
no code implementations • 21 Feb 2020 • Micah Goldblum, Avi Schwarzschild, Ankit B. Patel, Tom Goldstein
Algorithmic trading systems are often completely automated, and deep learning is increasingly receiving attention in this domain.
no code implementations • 25 Sep 2019 • Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debhath, Anjul Patney, Ankit B. Patel, Anima Anandkumar
Generative adversarial networks (GANs) have achieved great success at generating realistic samples.
no code implementations • 25 Sep 2019 • Varun Suriyanarayana, Onur Tavaslioglu, Ankit B. Patel, Andrew J. Schaefer
We use deep value-based reinforcement learning to learn a pivoting strategy that at each iteration chooses between two of the most popular pivot rules -- Dantzig and steepest edge.
no code implementations • ICLR 2019 • Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Swarat Chaudhuri, Ankit B. Patel
We study the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
no code implementations • ICLR 2019 • Nhat Ho, Tan Nguyen, Ankit B. Patel, Anima Anandkumar, Michael. I. Jordan, Richard G. Baraniuk
The conjugate prior yields a new regularizer for learning based on the paths rendered in the generative model for training CNNs–the Rendering Path Normalization (RPN).
no code implementations • 27 Feb 2019 • Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
no code implementations • NeurIPS 2016 • Ankit B. Patel, Tan Nguyen, Richard G. Baraniuk
We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables.
no code implementations • 6 Dec 2016 • Tan Nguyen, Wanjia Liu, Ethan Perez, Richard G. Baraniuk, Ankit B. Patel
Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning.
no code implementations • 17 Aug 2015 • Ali Mousavi, Ankit B. Patel, Richard G. Baraniuk
In this paper, we develop a new framework for sensing and recovering structured signals.
1 code implementation • 2 Apr 2015 • Ankit B. Patel, Tan Nguyen, Richard G. Baraniuk
A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation.