1 code implementation • 10 Apr 2024 • Jinyang Liu, Wondmgezahu Teshome, Sandesh Ghimire, Mario Sznaier, Octavia Camps
Solving image and video jigsaw puzzles poses the challenging task of rearranging image fragments or video frames from unordered sequences to restore meaningful images and video sequences.
no code implementations • 23 Oct 2023 • Armand Comas-Massagué, Yilun Du, Christian Fernandez, Sandesh Ghimire, Mario Sznaier, Joshua B. Tenenbaum, Octavia Camps
In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory.
no code implementations • 25 Jul 2023 • Nilesh Kumar, Prashnna K. Gyawali, Sandesh Ghimire, Linwei Wang
To this end, we propose a novel object-centric data augmentation model that is able to learn the shape variations for the objects of interest and augment the object in place without modifying the rest of the image.
no code implementations • 9 Feb 2023 • Sandesh Ghimire, Jinyang Liu, Armand Comas, Davin Hill, Aria Masoomi, Octavia Camps, Jennifer Dy
We demonstrate that looking from geometric perspective enables us to answer many of these questions and provide new interpretations to some known results.
no code implementations • 5 Feb 2023 • Sandesh Ghimire, Armand Comas, Davin Hill, Aria Masoomi, Octavia Camps, Jennifer Dy
Towards the direction of having more control over image manipulation and conditional generation, we propose to learn image components in an unsupervised manner so that we can compose those components to generate and manipulate images in informed manner.
1 code implementation • 5 Oct 2022 • Davin Hill, Aria Masoomi, Max Torop, Sandesh Ghimire, Jennifer Dy
In this work we propose the Gaussian Process Explanation UnCertainty (GPEC) framework, which generates a unified uncertainty estimate combining decision boundary-aware uncertainty with explanation function approximation uncertainty.
no code implementations • 8 Nov 2021 • Max Torop, Sandesh Ghimire, Wenqian Liu, Dana H. Brooks, Octavia Camps, Milind Rajadhyaksha, Jennifer Dy, Kivanc Kose
There are limited works showing the efficacy of unsupervised Out-of-Distribution (OOD) methods on complex medical data.
no code implementations • 1 Oct 2021 • Armand Comas, Sandesh Ghimire, Haolin Li, Mario Sznaier, Octavia Camps
Human interpretation of the world encompasses the use of symbols to categorize sensory inputs and compose them in a hierarchical manner.
no code implementations • NeurIPS 2021 • Sandesh Ghimire, Aria Masoomi, Jennifer Dy
To achieve this objective, we 1) present a novel construction of the discriminator in the Reproducing Kernel Hilbert Space (RKHS), 2) theoretically relate the error probability bound of the KL estimates to the complexity of the discriminator in the RKHS space, 3) present a scalable way to control the complexity (RKHS norm) of the discriminator for a reliable estimation of KL divergence, and 4) prove the consistency of the proposed estimator.
1 code implementation • 23 Sep 2020 • Prashnna Kumar Gyawali, Sandesh Ghimire, Linwei Wang
On three benchmark data sets and one real-world biomedical data set, we demonstrate that this combined regularization results in improved generalization performance of SSL when learning from a small amount of labeled data.
no code implementations • 4 Aug 2020 • Sandesh Ghimire, Satyananda Kashyap, Joy T. Wu, Alexandros Karargyris, Mehdi Moradi
Through pneumonia-classification experiments on multi-source chest X-ray datasets, we show that this algorithm helps in improving classification accuracy on a new source of X-ray dataset.
no code implementations • 18 Jul 2020 • Xiajun Jiang, Sandesh Ghimire, Jwala Dhamala, Zhiyuan Li, Prashnna Kumar Gyawali, Linwei Wang
However, many reconstruction problems involve imaging physics that are dependent on the underlying non-Euclidean geometry.
1 code implementation • 22 May 2020 • Prashnna Kumar Gyawali, Sandesh Ghimire, Pradeep Bajracharya, Zhiyuan Li, Linwei Wang
In this work, we argue that regularizing the global smoothness of neural functions by filling the void in between data points can further improve SSL.
no code implementations • 15 May 2020 • Jwala Dhamala, Sandesh Ghimire, John L. Sapp, B. Milan Horácek, Linwei Wang
The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models.
no code implementations • 25 Feb 2020 • Sandesh Ghimire, Prashnna K Gyawali, Linwei Wang
Based on this theory, we then present a scalable way to control the complexity of the discriminator for a reliable estimation of KL divergence.
1 code implementation • 3 Sep 2019 • Prashnna Kumar Gyawali, Zhiyuan Li, Cameron Knight, Sandesh Ghimire, B. Milan Horacek, John Sapp, Linwei Wang
We note that the independence within and the complexity of the latent density are two different properties we constrain when regularizing the posterior density: while the former promotes the disentangling ability of VAE, the latter -- if overly limited -- creates an unnecessary competition with the data reconstruction objective in VAE.
1 code implementation • 22 Jul 2019 • Prashnna Kumar Gyawali, Zhiyuan Li, Sandesh Ghimire, Linwei Wang
In this work, we hypothesize -- from the generalization perspective -- that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space.
1 code implementation • 1 Jul 2019 • Jwala Dhamala, Sandesh Ghimire, John L. Sapp, B. Milan Horacek, Linwei Wang
In this paper, we present a novel graph convolutional VAE to allow generative modeling of non-Euclidean data, and utilize it to embed Bayesian optimization of large graphs into a small latent space.
no code implementations • 12 May 2019 • Sandesh Ghimire, Jwala Dhamala, Prashnna Kumar Gyawali, John L. Sapp, B. Milan Horacek, Linwei Wang
We introduce a novel model-constrained inference framework that replaces conventional physiological models with a deep generative model trained to generate TMP sequences from low-dimensional generative factors.
1 code implementation • 5 Mar 2019 • Sandesh Ghimire, Prashnna Kumar Gyawali, Jwala Dhamala, John L. Sapp, Milan Horacek, Linwei Wang
Deep learning networks have shown state-of-the-art performance in many image reconstruction problems.
no code implementations • 31 Oct 2018 • Prashnna K Gyawali, Cameron Knight, Sandesh Ghimire, B. Milan Horacek, John L. Sapp, Linwei Wang
While deep representation learning has become increasingly capable of separating task-relevant representations from other confounding factors in the data, two significant challenges remain.
no code implementations • 12 Oct 2018 • Sandesh Ghimire, Prashnna Kumar Gyawali, John L. Sapp, Milan Horacek, Linwei Wang
The results demonstrate that the generalization ability of an inverse reconstruction network can be improved by constrained stochasticity combined with global aggregation of temporal information in the latent space.