1 code implementation • 28 Mar 2024 • Mingxing Rao, Yinhong Qin, Soheil Kolouri, Jie Ying Wu, Daniel Moyer
Purpose: Surgical video is an important data stream for gesture recognition.
no code implementations • 11 Mar 2024 • Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri
However, traditional dataset distillation approaches often struggle to scale effectively with high-resolution images and more complex architectures due to the limitations in bi-level optimization.
no code implementations • 6 Feb 2024 • Yikun Bai, Rocio Diaz Martin, Hengrong Du, Ashkan Shahbazi, Soheil Kolouri
The partial Gromov-Wasserstein (PGW) problem facilitates the comparison of measures with unequal masses residing in potentially distinct metric spaces, thereby enabling unbalanced and partial matching across these spaces.
no code implementations • 4 Feb 2024 • Huy Tran, Yikun Bai, Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Rocio Diaz Martin, Soheil Kolouri
Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning.
no code implementations • 21 Nov 2023 • Ali Abbasi, Chayne Thrash, Elaheh Akbari, Daniel Zhang, Soheil Kolouri
Given a trained model and a subset of training data designated to be forgotten (i. e., the "forget set"), we introduce a three-step process, named CovarNav, to facilitate this forgetting.
no code implementations • 20 Nov 2023 • Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash, Soheil Kolouri
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning.
no code implementations • 9 Oct 2023 • Rocio Diaz Martin, Ivan Medri, Yikun Bai, Xinran Liu, Kangbai Yan, Gustavo K. Rohde, Soheil Kolouri
The optimal transport problem for measures supported on non-Euclidean spaces has recently gained ample interest in diverse applications involving representation learning.
1 code implementation • 4 Oct 2023 • Soroush Abbasi Koohpayegani, KL Navaneet, Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash
For instance, in larger models, even a rank one decomposition might exceed the number of parameters truly needed for adaptation.
no code implementations • 27 Sep 2023 • Yikun Bai, Huy Tran, Steven B. Damelin, Soheil Kolouri
In this paper, we approach the point-cloud registration problem through the lens of optimal transport theory and first propose a comprehensive set of non-rigid registration methods based on the optimal partial transportation problem.
no code implementations • 25 Jul 2023 • Xinran Liu, Yikun Bai, Huy Tran, Zhanqi Zhu, Matthew Thorpe, Soheil Kolouri
In this paper, we introduce partial transport $\mathrm{L}^{p}$ distances as a new family of metrics for comparing generic signals, benefiting from the robustness of partial transport distances.
no code implementations • 8 Jun 2023 • Ashkan Shahbazi, Abihith Kothapalli, Xinran Liu, Robert Sheng, Soheil Kolouri
Our findings reveal that: 1) complex pooling methods, such as transport-based or attention-based poolings, can significantly boost the performance of simple backbones, but the benefits diminish for more complex backbones, 2) even complex backbones can benefit from pooling layers in low data scenarios, 3) surprisingly, the choice of pooling layers can have a more significant impact on the model's performance than adjusting the width and depth of the backbone, and 4) pairwise combination of pooling layers can significantly improve the performance of a fixed backbone.
1 code implementation • 18 May 2023 • Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu, Xinran Liu, Shirin Dora, Cong Liu, Soheil Kolouri, Andrea Soltoggio
The key idea is that the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning.
no code implementations • 10 Feb 2023 • Yuzhe Lu, Zhenlin Wang, Runtian Zhai, Soheil Kolouri, Joseph Campbell, Katia Sycara
Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models as even subtle changes could incur significant performance drops.
1 code implementation • 7 Feb 2023 • Yikun Bai, Ivan Medri, Rocio Diaz Martin, Rana Muhammad Shahroz Khan, Soheil Kolouri
To address these limitations, variants of the OT problem, including unbalanced OT, Optimal partial transport (OPT), and Hellinger Kantorovich (HK), have been proposed.
1 code implementation • 21 Jan 2023 • Andrea Soltoggio, Eseoghene Ben-Iwhiwhu, Christos Peridis, Pawel Ladosz, Jeffery Dick, Praveen K. Pilly, Soheil Kolouri
This paper introduces a set of formally defined and transparent problems for reinforcement learning algorithms with the following characteristics: (1) variable degrees of observability (non-Markov observations), (2) distal and sparse rewards, (3) variable and hierarchical reward structure, (4) multiple-task generation, (5) variable problem complexity.
no code implementations • 18 Jan 2023 • Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sébastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
1 code implementation • 21 Dec 2022 • Eseoghene Ben-Iwhiwhu, Saptarshi Nath, Praveen K. Pilly, Soheil Kolouri, Andrea Soltoggio
The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.
2 code implementations • CVPR 2023 • Yikun Bai, Berhnard Schmitzer, Mathew Thorpe, Soheil Kolouri
Optimal transport (OT) has become exceedingly popular in machine learning, data science, and computer vision.
no code implementations • 26 Oct 2022 • Zihao Wu, Huy Tran, Hamed Pirsiavash, Soheil Kolouri
Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting.
1 code implementation • 24 Aug 2022 • Xinran Liu, Yikun Bai, Yuzhe Lu, Andrea Soltoggio, Soheil Kolouri
Lastly, we leverage the 2-Wasserstein embedding framework to embed tasks into a vector space in which the Euclidean distance between the embedded points approximates the proposed 2-Wasserstein distance between tasks.
no code implementations • 22 Aug 2022 • Meiyi Li, Soheil Kolouri, Javad Mohammadi
We demonstrate the performance of our proposed method in quadratic programming in the context of the optimal power dispatch (critical to the resiliency of our electric grid) and a constrained non-convex optimization in the context of image registration problems.
2 code implementations • ICCV 2023 • Parsa Nooralinejad, Ali Abbasi, Soroush Abbasi Koohpayegani, Kossar Pourahmadi Meibodi, Rana Muhammad Shahroz Khan, Soheil Kolouri, Hamed Pirsiavash
We demonstrate that a deep model can be reparametrized as a linear combination of several randomly initialized and frozen deep models in the weight space.
no code implementations • 12 Mar 2022 • Ali Abbasi, Parsa Nooralinejad, Vladimir Braverman, Hamed Pirsiavash, Soheil Kolouri
Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years.
no code implementations • 8 Feb 2022 • Xinran Liu, Yuzhe Lu, Ali Abbasi, Meiyi Li, Javad Mohammadi, Soheil Kolouri
In addition, we propose two alternative approaches for learning such parametric functions, with and without a solver in the LOOP.
1 code implementation • 11 Dec 2021 • Yuzhe Lu, Xinran Liu, Andrea Soltoggio, Soheil Kolouri
This paper focuses on non-parametric and data-independent learning from set-structured data using approximate nearest neighbor (ANN) solutions, particularly locality-sensitive hashing.
1 code implementation • NeurIPS 2021 • Navid Naderializadeh, Joseph Comer, Reed Andrews, Heiko Hoffmann, Soheil Kolouri
Learning representations from sets has become increasingly important with many applications in point cloud processing, graph learning, image/video recognition, and object detection.
no code implementations • 17 Apr 2021 • Haoran Li, Aditya Krishnan, Jingfeng Wu, Soheil Kolouri, Praveen K. Pilly, Vladimir Braverman
In practice and due to computational constraints, most SR methods crudely approximate the importance matrix by its diagonal.
no code implementations • 5 Mar 2021 • Navid Naderializadeh, Soheil Kolouri, Joseph F. Comer, Reed W. Andrews, Heiko Hoffmann
An increasing number of machine learning tasks deal with learning representations from set-structured data.
1 code implementation • ICLR 2021 • Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann
We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks.
Ranked #3 on Graph Classification on RE-M5K
no code implementations • ICLR 2020 • Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
no code implementations • ICLR 2020 • Soheil Kolouri, Nicholas A. Ketz, Andrea Soltoggio, Praveen K. Pilly
Deep neural networks suffer from the inability to preserve the learned data representation (i. e., catastrophic forgetting) in domains where the input data distribution is non-stationary, and it changes during training.
3 code implementations • 7 Apr 2020 • Mohammad Shifat-E-Rabbi, Xuwang Yin, Abu Hasnat Mohammad Rubaiyat, Shiying Li, Soheil Kolouri, Akram Aldroubi, Jonathan M. Nichols, Gustavo K. Rohde
We present a new supervised image classification method applicable to a broad class of image deformation models.
1 code implementation • NeurIPS 2020 • Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Şimşekli
The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence' between one-dimensional random projections of the two measures.
no code implementations • 28 Feb 2020 • Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Shahin Shahrampour
Probability metrics have become an indispensable part of modern statistics and machine learning, and they play a quintessential role in various applications, including statistical hypothesis testing and generative modeling.
1 code implementation • 21 Sep 2019 • Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick, Yang Hu, Nicholas Ketz, Soheil Kolouri, Jeffrey L. Krichmar, Praveen Pilly, Andrea Soltoggio
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA).
no code implementations • 4 Jul 2019 • Alex Gabourie, Mohammad Rostami, Philip Pope, Soheil Kolouri, Kyungnam Kim
We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized.
1 code implementation • 4 Jul 2019 • Soheil Kolouri, Xuwang Yin, Gustavo K. Rohde
Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks.
1 code implementation • CVPR 2020 • Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, Heiko Hoffmann
In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan attacks) on deep convolutional neural networks (CNNs).
no code implementations • 10 Jun 2019 • Mohammad Rostami, Soheil Kolouri, Zak Murez, Yuri Owekcho, Eric Eaton, Kuyngnam Kim
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes.
no code implementations • 10 Jun 2019 • Mohammad Rostami, Soheil Kolouri, James McClelland, Praveen Pilly
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge.
1 code implementation • 27 May 2019 • Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
1 code implementation • ICLR 2019 • Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde
In this paper we use the geometric properties of the optimal transport (OT) problem and the Wasserstein distances to define a prior distribution for the latent space of an auto-encoder.
no code implementations • 20 Mar 2019 • Shahin Shahrampour, Soheil Kolouri
Random features provide a practical framework for large-scale kernel approximation and supervised learning.
no code implementations • 11 Mar 2019 • Mohammad Rostami, Soheil Kolouri, Praveen K. Pilly
We sample from this distribution and utilize experience replay to avoid forgetting and simultaneously accumulate new knowledge to the abstract distribution in order to couple the current task with past experience.
no code implementations • 6 Mar 2019 • Nicholas Ketz, Soheil Kolouri, Praveen Pilly
Here we propose a method to continually learn these internal world models through the interleaving of internally generated episodes of past experiences (i. e., pseudo-rehearsal).
no code implementations • 2 Mar 2019 • Soheil Kolouri, Nicholas Ketz, Xinyun Zou, Jeffrey Krichmar, Praveen Pilly
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks.
no code implementations • 16 Feb 2019 • Xinyun Zou, Soheil Kolouri, Praveen K. Pilly, Jeffrey L. Krichmar
In uncertain domains, the goals are often unknown and need to be predicted by the organism or system.
1 code implementation • NeurIPS 2019 • Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau, Gustavo K. Rohde
The SW distance, specifically, was shown to have similar properties to the Wasserstein distance, while being much simpler to compute, and is therefore used in various applications including generative modeling and general supervised/unsupervised learning.
no code implementations • 1 Dec 2018 • Phillip Pope, Soheil Kolouri, Mohammad Rostrami, Charles Martin, Heiko Hoffmann
Functional groups (FGs) are molecular substructures that are served as a foundation for analyzing and predicting chemical properties of molecules.
5 code implementations • 5 Apr 2018 • Soheil Kolouri, Phillip E. Pope, Charles E. Martin, Gustavo K. Rohde
In short, we regularize the autoencoder loss with the sliced-Wasserstein distance between the distribution of the encoded training samples and a predefined samplable distribution.
no code implementations • CVPR 2018 • Zak Murez, Soheil Kolouri, David Kriegman, Ravi Ramamoorthi, Kyungnam Kim
This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network.
2 code implementations • CVPR 2018 • Soheil Kolouri, Gustavo K. Rohde, Heiko Hoffmann
In contrast to the KL-divergence, the energy landscape for the sliced-Wasserstein distance is more well-behaved and therefore more suitable for a stochastic gradient descent scheme to obtain the optimal GMM parameters.
no code implementations • 15 Sep 2017 • Mohammad Rostami, Soheil Kolouri, Kyungnam Kim, Eric Eaton
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience.
no code implementations • 12 Sep 2017 • Soheil Kolouri, Mohammad Rostami, Yuri Owechko, Kyungnam Kim
A classic approach toward zero-shot learning (ZSL) is to map the input domain to a set of semantically meaningful attributes that could be used later on to classify unseen classes of data (e. g. visual data).
no code implementations • CVPR 2017 • Shay Deutsch, Soheil Kolouri, Kyungnam Kim, Yuri Owechko, Stefano Soatto
We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs.
no code implementations • 14 May 2017 • Shinjini Kundu, Soheil Kolouri, Kirk I Erickson, Arthur F Kramer, Edward McAuley, Gustavo K. Rohde
Disease in the brain is often associated with subtle, spatially diffuse, or complex tissue changes that may lie beneath the level of gross visual inspection, even on magnetic resonance imaging (MRI).
no code implementations • 27 Sep 2016 • Matthew Thorpe, Serim Park, Soheil Kolouri, Gustavo K. Rohde, Dejan Slepčev
Transport based distances, such as the Wasserstein distance and earth mover's distance, have been shown to be an effective tool in signal and image analysis.
no code implementations • 15 Sep 2016 • Soheil Kolouri, Serim Park, Matthew Thorpe, Dejan Slepčev, Gustavo K. Rohde
Transport-based techniques for signal and data analysis have received increased attention recently.
no code implementations • 10 Nov 2015 • Soheil Kolouri, Se Rim Park, Gustavo K. Rohde
Invertible image representation methods (transforms) are routinely employed as low-level image processing operations based on which feature extraction and recognition algorithms are developed.
no code implementations • CVPR 2016 • Soheil Kolouri, Yang Zou, Gustavo K. Rohde
Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions.
no code implementations • 21 Jul 2015 • Se Rim Park, Soheil Kolouri, Shinjini Kundu, Gustavo Rohde
Discriminating data classes emanating from sensors is an important problem with many applications in science and technology.
no code implementations • CVPR 2015 • Soheil Kolouri, Gustavo K. Rohde
Extracting high-resolution information from highly degraded facial images is an important problem with several applications in science and technology.