Search Results for author:
Found 62 papers, 22 papers with code
Zero-shot Prompt-based Video Encoder for Surgical Gesture Recognition
Purpose: Surgical video is an important data stream for gesture recognition.
One Category One Prompt: Dataset Distillation using Diffusion Models
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.
Efficient Solvers for Partial Gromov-Wasserstein
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.
Stereographic Spherical Sliced Wasserstein Distances
Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning.
CovarNav: Machine Unlearning via Model Inversion and Covariance Navigation
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.
BrainWash: A Poisoning Attack to Forget in Continual Learning
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning.
LCOT: Linear circular optimal transport
The optimal transport problem for measures supported on non-Euclidean spaces has recently gained ample interest in diverse applications involving representation learning.
NOLA: Networks as Linear Combination of Low Rank Random Basis
For instance, in larger models, even a rank one decomposition might exceed the number of parameters truly needed for adaptation.
Partial Transport for Point-Cloud Registration
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.
PT$\mathrm{L}^{p}$: Partial Transport $\mathrm{L}^{p}$ Distances
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.
Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification
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.
Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
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.
Predicting Out-of-Distribution Error with Confidence Optimal Transport
Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models as even subtle changes could incur significant performance drops.
Linear Optimal Partial Transport Embedding
To address these limitations, variants of the OT problem, including unbalanced OT, Optimal partial transport (OPT), and Hellinger Kantorovich (HK), have been proposed.
The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning
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.
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
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.
Lifelong Reinforcement Learning with Modulating Masks
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.
Sliced Optimal Partial Transport
Optimal transport (OT) has become exceedingly popular in machine learning, data science, and computer vision.
Is Multi-Task Learning an Upper Bound for Continual Learning?
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.
Wasserstein Task Embedding for Measuring Task Similarities
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.
Learning to Solve Optimization Problems with Hard Linear Constraints
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.
PRANC: Pseudo RAndom Networks for Compacting deep models
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.
Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations
Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years.
Teaching Networks to Solve Optimization Problems
In addition, we propose two alternative approaches for learning such parametric functions, with and without a solver in the LOOP.
SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings
This paper focuses on non-parametric and data-independent learning from set-structured data using approximate nearest neighbor (ANN) solutions, particularly locality-sensitive hashing.
Pooling by Sliced-Wasserstein Embedding
Learning representations from sets has become increasingly important with many applications in point cloud processing, graph learning, image/video recognition, and object detection.
Lifelong Learning with Sketched Structural Regularization
In practice and due to computational constraints, most SR methods crudely approximate the importance matrix by its diagonal.
Set Representation Learning with Generalized Sliced-Wasserstein Embeddings
An increasing number of machine learning tasks deal with learning representations from set-structured data.
Wasserstein Embedding for Graph Learning
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
GAT: Generative Adversarial Training for Adversarial Example Detection and Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Sliced Cramer Synaptic Consolidation for Preserving Deeply Learned Representations
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.
Radon cumulative distribution transform subspace modeling for image classification
We present a new supervised image classification method applicable to a broad class of image deformation models.
Statistical and Topological Properties of Sliced Probability Divergences
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.
Generalized Sliced Distances for Probability Distributions
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.
Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
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).
Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
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.
Neural Networks, Hypersurfaces, and Radon Transforms
Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks.
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs
In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan attacks) on deep convolutional neural networks (CNNs).
Zero-Shot Image Classification Using Coupled Dictionary Embedding
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes.
Generative Continual Concept Learning
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.
GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Sliced Wasserstein Auto-Encoders
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.
On Sampling Random Features From Empirical Leverage Scores: Implementation and Theoretical Guarantees
Random features provide a practical framework for large-scale kernel approximation and supervised learning.
Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay
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.
Continual Learning Using World Models for Pseudo-Rehearsal
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).
Attention-Based Structural-Plasticity
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.
Neuromodulated Goal-Driven Perception in Uncertain Domains
In uncertain domains, the goals are often unknown and need to be predicted by the organism or system.
Generalized Sliced Wasserstein Distances
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.
Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks
Functional groups (FGs) are molecular substructures that are served as a foundation for analyzing and predicting chemical properties of molecules.
Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
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.
Image to Image Translation for Domain Adaptation
This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network.
Sliced Wasserstein Distance for Learning Gaussian Mixture Models
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.
Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition
Lifelong machine learning methods acquire knowledge over a series of consecutive tasks, continually building upon their experience.
Joint Dictionaries for Zero-Shot Learning
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).
Zero Shot Learning via Multi-Scale Manifold Regularization
We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs.
Discovery and visualization of structural biomarkers from MRI using transport-based morphometry
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).
A Transportation $L^p$ Distance for Signal Analysis
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.
Transport-based analysis, modeling, and learning from signal and data distributions
Transport-based techniques for signal and data analysis have received increased attention recently.
The Radon cumulative distribution transform and its application to image classification
Invertible image representation methods (transforms) are routinely employed as low-level image processing operations based on which feature extraction and recognition algorithms are developed.
Sliced Wasserstein Kernels for Probability Distributions
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.
The Cumulative Distribution Transform and Linear Pattern Classification
Discriminating data classes emanating from sensors is an important problem with many applications in science and technology.
Transport-Based Single Frame Super Resolution of Very Low Resolution Face Images
Extracting high-resolution information from highly degraded facial images is an important problem with several applications in science and technology.
