Search Results for author:
Found 123 papers, 49 papers with code
IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities.
Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein Projection
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets.
Sparse Training of Discrete Diffusion Models for Graph Generation
In this work, we introduce SparseDiff, a denoising diffusion model for graph generation that is able to exploit sparsity during its training phase.
Castor: Causal Temporal Regime Structure Learning
The task of uncovering causal relationships among multivariate time series data stands as an essential and challenging objective that cuts across a broad array of disciplines ranging from climate science to healthcare.
Tertiary Lymphoid Structures Generation through Graph-based Diffusion
In particular, we show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content, a well-established biomarker for evaluating the cancer progression in oncology research.
Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels
Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models.
A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation
To evaluate the robustness of NMT models to our attack, we propose enhancements to existing black-box word-replacement-based attacks by incorporating output translations of the target NMT model and the output logits of a classifier within the attack process.
Online Network Source Optimization with Graph-Kernel MAB
To achieve sample efficiency, we describe the network processes with an adaptive graph dictionary model, which typically leads to sparse spectral representations.
DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications
This results in our DomainAdaptiveAREstimator (DARE) attribution robustness estimator, allowing us to properly characterize the domain-specific robustness of faithful explanations.
A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models
First, we propose an optimization problem to generate adversarial examples that are semantically similar to the original sentences but destroy the translation generated by the target NMT model.
Flexible Channel Dimensions for Differentiable Architecture Search
Finding optimal channel dimensions (i. e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints.
Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions
In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling such corruptions.
Bures-Wasserstein Means of Graphs
Finding the mean of sampled data is a fundamental task in machine learning and statistics.
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks, while negating them leads to task forgetting.
SequeL: A Continual Learning Library in PyTorch and JAX
Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge.
Knowledge-Distilled Graph Neural Networks for Personalized Epileptic Seizure Detection
We consider two cases (a) when a single student is learnt for all the patients using preselected channels; and (b) when personalized students are learnt for every individual patient, with personalized channel selection using a Gumbelsoftmax approach.
Hierarchical Training of Deep Neural Networks Using Early Exiting
In this study, a novel hierarchical training method for deep neural networks is proposed that uses early exits in a divided architecture between edge and cloud workers to reduce the communication cost, training runtime and privacy concerns.
Targeted Adversarial Attacks against Neural Machine Translation
In this paper, we propose a new targeted adversarial attack against NMT models.
MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation
This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms.
TransFool: An Adversarial Attack against Neural Machine Translation Models
Deep neural networks have been shown to be vulnerable to small perturbations of their inputs, known as adversarial attacks.
Adversarial training with informed data selection
With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance.
Estimating the Adversarial Robustness of Attributions in Text with Transformers
Finally, with experiments on several text classification architectures, we show that TEA consistently outperforms current state-of-the-art AR estimators, yielding perturbations that alter explanations to a greater extent while being more fluent and less perceptible.
SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud
However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e. g., from Waymo (64-beam) to nuScenes (32-beam).
Maximum Likelihood Distillation for Robust Modulation Classification
Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular.
A Meta-GNN approach to personalized seizure detection and classification
In this paper, we propose a personalized seizure detection and classification framework that quickly adapts to a specific patient from limited seizure samples.
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts.
Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments.
CLAD: A Contrastive Learning based Approach for Background Debiasing
Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification.
DiGress: Discrete Denoising diffusion for graph generation
This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes.
Catastrophic overfitting can be induced with discriminative non-robust features
Through extensive experiments we analyze this novel phenomenon and discover that the presence of these easy features induces a learning shortcut that leads to CO. Our findings provide new insights into the mechanisms of CO and improve our understanding of the dynamics of AT.
Fooling Explanations in Text Classifiers
TEF can significantly decrease the correlation between unchanged and perturbed input attributions, which shows that all models and explanation methods are susceptible to TEF perturbations.
Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling
Specifically, adaptive spherical wavelets are learned with a lifting structure that consists of trainable lifting operators (i. e., update and predict operators).
Empirical Advocacy of Bio-inspired Models for Robust Image Recognition
There are continuous attempts to use features of the human visual system to improve the robustness of neural networks to data perturbations.
U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search
Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference.
Hardware Aware Neural Architecture Search
Image Classification
+1
Scale-out Systolic Arrays
In this work, we study three key pillars in multi-pod systolic array designs, namely array granularity, interconnect, and tiling.
On the benefits of knowledge distillation for adversarial robustness
To that end, we present Adversarial Knowledge Distillation (AKD), a new framework to improve a model's robust performance, consisting on adversarially training a student on a mixture of the original labels and the teacher outputs.
Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers
Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples.
Data augmentation with mixtures of max-entropy transformations for filling-level classification
We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification.
PRIME: A few primitives can boost robustness to common corruptions
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data.
Ranked #28 on
Domain Generalization
on ImageNet-C
Distributed Graph Learning with Smooth Data Priors
We propose here a novel distributed graph learning algorithm, which permits to infer a graph from signal observations on the nodes under the assumption that the data is smooth on the target graph.
A Structured Dictionary Perspective on Implicit Neural Representations
Leveraging results from harmonic analysis and deep learning theory, we show that most INR families are analogous to structured signal dictionaries whose atoms are integer harmonics of the set of initial mapping frequencies.
Top-N: Equivariant set and graph generation without exchangeability
This work addresses one-shot set and graph generation, and, more specifically, the parametrization of probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs.
An evaluation of quality and robustness of smoothed explanations
However, a combination of additive and non-additive attacks can still manipulate these explanations, which reveals shortcomings in their robustness properties.
Graph Convolutional Networks via Adaptive Filter Banks
Graph convolutional networks have been a powerful tool in representation learning of networked data.
FGOT: Graph Distances based on Filters and Optimal Transport
We tackle the problem of graph alignment by computing graph permutations that minimise our new filter distances, which implicitly solves the graph comparison problem.
Graph Neural Networks With Lifting-based Adaptive Graph Wavelets
To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information.
OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression
State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs).
Privacy-Preserving Image Acquisition Using Trainable Optical Kernel
Also, in contrast with the previous optical privacy-preserving methods that cannot be trained, our method is data-driven and optimized for the specific application at hand.
Message Passing in Graph Convolution Networks via Adaptive Filter Banks
Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank.
What can linearized neural networks actually say about generalization?
For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK only provides a rough first-order approximation.
SafeAMC: Adversarial training for robust modulation recognition models
We propose to use adversarial training, which consists of fine-tuning the model with adversarial perturbations, to increase the robustness of automatic modulation recognition (AMC) models.
A neural anisotropic view of underspecification in deep learning
In this work, we propose to study this problem from a geometric perspective with the aim to understand two key characteristics of neural network solutions in underspecified settings: how is the geometry of the learned function related to the data representation?
Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs
Multivariate time series forecasting poses challenges as the variables are intertwined in time and space, like in the case of traffic signals.
Ranked #7 on
Traffic Prediction
on PEMS-BAY
(RMSE metric)
Multilayer Graph Clustering with Optimized Node Embedding
To do so, we propose to learn a clustering-friendly embedding of the graph nodes by solving an optimization problem that involves a fidelity term to the layers of a given multilayer graph, and a regularization on the (single-layer) graph induced by the embedding.
On the benefits of robust models in modulation recognition
When analyzing these vulnerable models we found that adversarial perturbations do not shift the symbols towards the nearest classes in constellation space.
Bio-inspired Robustness: A Review
Many studies have tried to add features of the human visual system to DCNNs to make them robust against adversarial attacks.
Self-Supervision by Prediction for Object Discovery in Videos
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data.
Improving filling level classification with adversarial training
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass.
QUACKIE: A NLP Classification Task With Ground Truth Explanations
NLP Interpretability aims to increase trust in model predictions.
On the Granularity of Explanations in Model Agnostic NLP Interpretability
Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response.
Multilayer Clustered Graph Learning
In this paper, we aim at analyzing multilayer graphs by properly combining the information provided by individual layers, while preserving the specific structure that allows us to eventually identify communities or clusters that are crucial in the analysis of graph data.
FiGLearn: Filter and Graph Learning using Optimal Transport
We cast a new optimisation problem that minimises the Wasserstein distance between the distribution of the signal observations and the filtered signal distribution model.
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
In this article, we provide an in-depth review of the field of adversarial robustness in deep learning, and give a self-contained introduction to its main notions.
FAR: A General Framework for Attributional Robustness
Therefore, we define a novel generic framework for attributional robustness (FAR) as general problem formulation for training models with robust attributions.
Modurec: Recommender Systems with Feature and Time Modulation
Current state of the art algorithms for recommender systems are mainly based on collaborative filtering, which exploits user ratings to discover latent factors in the data.
node2coords: Graph Representation Learning with Wasserstein Barycenters
In the decoder, the node connectivity descriptors are reconstructed as Wasserstein barycenters of the graph structural patterns.
Graph signal processing for machine learning: A review and new perspectives
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.
Towards robust sensing for Autonomous Vehicles: An adversarial perspective
Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions.
Building powerful and equivariant graph neural networks with structural message-passing
We address this problem and propose a powerful and equivariant message-passing framework based on two ideas: first, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node.
Graph Pooling with Node Proximity for Hierarchical Representation Learning
In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.
Neural Anisotropy Directions
In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers.
GeoDA: a geometric framework for black-box adversarial attacks
We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only generate a small number of queries, each of them returning the top-$1$ label of the classifier.
Wasserstein-based Graph Alignment
We propose a novel method for comparing non-aligned graphs of different sizes, based on the Wasserstein distance between graph signal distributions induced by the respective graph Laplacian matrices.
Hold me tight! Influence of discriminative features on deep network boundaries
In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary.
Joint Graph-based Depth Refinement and Normal Estimation
Depth estimation is an essential component in understanding the 3D geometry of a scene, with numerous applications in urban and indoor settings.
Multi-view shape estimation of transparent containers
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions.
On the choice of graph neural network architectures
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals.
Imperceptible Adversarial Attacks on Tabular Data
Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions.
Mask Combination of Multi-layer Graphs for Global Structure Inference
Structure inference is an important task for network data processing and analysis in data science.
Forward-Backward Splitting for Optimal Transport based Problems
Experiments show that the proposed method leads to a significant improvement in terms of speed and performance with respect to the state of the art for domain adaptation on a continually rotating distribution coming from the standard two moon dataset.
iPool -- Information-based Pooling in Hierarchical Graph Neural Networks
In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs.
GOT: An Optimal Transport framework for Graph comparison
We present a novel framework based on optimal transport for the challenging problem of comparing graphs.
Geometry aware convolutional filters for omnidirectional images representation
In particular we propose an algorithm that adapts convolutional layers, which often serve as a core building block of a CNN, to the properties of omnidirectional images.
A geometry-inspired decision-based attack
The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples.
Graph heat mixture model learning
Graph inference methods have recently attracted a great interest from the scientific community, due to the large value they bring in data interpretation and analysis.
Stochastic Gradient Descent for Spectral Embedding with Implicit Orthogonality Constraint
In this paper, we propose a scalable algorithm for spectral embedding.
Robustness via curvature regularization, and vice versa
State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations.
SparseFool: a few pixels make a big difference
Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the input data.
Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise
In presence of sparse noise we propose kernel regression for predicting output vectors which are smooth over a given graph.
OrthoNet: Multilayer Network Data Clustering
We propose in this paper to extend the node clustering problem, that commonly considers only the network information, to a problem where both the network information and the node features are considered together for learning a clustering-friendly representation of the feature space.
Graph Laplacian mixture model
Graph learning methods have recently been receiving increasing interest as means to infer structure in datasets.
Isometric Transformation Invariant Graph-based Deep Neural Network
In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images.
Learning graphs from data: A signal representation perspective
The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data.
Empirical Study of the Topology and Geometry of Deep Networks
We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary.
Adaptive Quantization for Deep Neural Network
First, we propose a measurement to estimate the effect of parameter quantization errors in individual layers on the overall model prediction accuracy.
Graph Signal Processing: Overview, Challenges and Applications
Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.
Signal Processing
Geometric robustness of deep networks: analysis and improvement
We propose ManiFool as a simple yet scalable algorithm to measure the invariance of deep networks.
Convolutional neural networks on irregular domains based on approximate vertex-domain translations
We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure.
Graph-Based Classification of Omnidirectional Images
Omnidirectional cameras are widely used in such areas as robotics and virtual reality as they provide a wide field of view.
Graph learning under sparsity priors
If this is not possible, the data structure has to be inferred from the mere signal observations.
Robustness of classifiers to universal perturbations: a geometric perspective
Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers.
Classification regions of deep neural networks
The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space.
Graph-based Isometry Invariant Representation Learning
Learning transformation invariant representations of visual data is an important problem in computer vision.
Light Field Super-Resolution Via Graph-Based Regularization
We adopt a multi-frame alike super-resolution approach, where the complementary information in the different light field views is used to augment the spatial resolution of the whole light field.
Learning heat diffusion graphs
Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph.
Universal adversarial perturbations
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability.
Robustness of classifiers: from adversarial to random noise
Moreover, we quantify the robustness of classifiers in terms of the subspace dimension in the semi-random noise regime, and show that our bounds remarkably interpolate between the worst-case and random noise regimes.
Multi-modal image retrieval with random walk on multi-layer graphs
The analysis of large collections of image data is still a challenging problem due to the difficulty of capturing the true concepts in visual data.
DeepFool: a simple and accurate method to fool deep neural networks
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks.
Manitest: Are classifiers really invariant?
Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks.
Graph-based compression of dynamic 3D point cloud sequences
This paper addresses the problem of compression of 3D point cloud sequences that are characterized by moving 3D positions and color attributes.
Multi-task additive models with shared transfer functions based on dictionary learning
Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer functions.
Analysis of classifiers' robustness to adversarial perturbations
To the best of our knowledge, our results provide the first theoretical work that addresses the phenomenon of adversarial instability recently observed for deep networks.
Learning Laplacian Matrix in Smooth Graph Signal Representations
We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.
Multiscale Event Detection in Social Media
In this paper, we propose a novel approach towards multiscale event detection using social media data, which takes into account different temporal and spatial scales of events in the data.
Dictionary learning for fast classification based on soft-thresholding
The dictionary learning problem, which jointly learns the dictionary and linear classifier, is cast as a difference of convex (DC) program and solved efficiently with an iterative DC solver.
A Study of Image Analysis with Tangent Distance
As theoretical studies about the tangent distance algorithm have been largely overlooked, we present in this work a detailed performance analysis of this useful algorithm, which can eventually help its implementation.
Learning parametric dictionaries for graph signals
In sparse signal representation, the choice of a dictionary often involves a tradeoff between two desirable properties -- the ability to adapt to specific signal data and a fast implementation of the dictionary.
Analysis of Descent-Based Image Registration
We show that the area of this neighborhood increases at least quadratically with the smoothing filter size, which justifies the use of a smoothing step in image registration with local optimizers such as gradient descent.
Image registration with sparse approximations in parametric dictionaries
We examine in this paper the problem of image registration from the new perspective where images are given by sparse approximations in parametric dictionaries of geometric functions.
Tangent-based manifold approximation with locally linear models
Our objective is to discover a set of low dimensional affine subspaces that represents manifold data accurately while preserving the manifold's structure.
The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.
Navigation domain representation for interactive multiview imaging
In this paper, we propose a novel multiview data representation that permits to satisfy bandwidth and storage constraints in an interactive multiview streaming system.
