Search Results for author:
Found 85 papers, 43 papers with code
Functional Bilevel Optimization for Machine Learning
In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space.
On Good Practices for Task-Specific Distillation of Large Pretrained Models
Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks.
Fast Semi-supervised Unmixing using Non-convex Optimization
Our experimental results validate that enforcing the convexity constraint outperforms the sparsity prior for the endmember library.
Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation
This positions our approach as a versatile tool for various burst image processing applications.
Towards Real-World Focus Stacking with Deep Learning
Focus stacking is widely used in micro, macro, and landscape photography to reconstruct all-in-focus images from multiple frames obtained with focus bracketing, that is, with shallow depth of field and different focus planes.
Vision Transformers Need Registers
Transformers have recently emerged as a powerful tool for learning visual representations.
Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package
Additionally, we draw a critical comparison between advanced and conventional techniques from the three categories.
SUnAA: Sparse Unmixing using Archetypal Analysis
Unlike most conventional sparse unmixing methods, here the minimization problem is non-convex.
GloptiNets: Scalable Non-Convex Optimization with Certificates
We present a novel approach to non-convex optimization with certificates, which handles smooth functions on the hypercube or on the torus.
Combining multi-spectral data with statistical and deep-learning models for improved exoplanet detection in direct imaging at high contrast
Exoplanet detection by direct imaging is a difficult task: the faint signals from the objects of interest are buried under a spatially structured nuisance component induced by the host star.
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection often performed manually.
Semi-supervised learning made simple with self-supervised clustering
Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations.
Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers
We introduce a novel self-attention mechanism, which we call CSA (Chromatic Self-Attention), which extends the notion of attention scores to attention _filters_, independently modulating the feature channels.
Ranked #1 on
Graph Regression
on ZINC-500k
DINOv2: Learning Robust Visual Features without Supervision
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
Ranked #1 on
Image Classification
on CIFAR-10
(using extra training data)
Sequential Counterfactual Risk Minimization
Counterfactual Risk Minimization (CRM) is a framework for dealing with the logged bandit feedback problem, where the goal is to improve a logging policy using offline data.
Learning Reward Functions for Robotic Manipulation by Observing Humans
Unlike prior work on leveraging human videos to teach robots, our method, Human Offline Learned Distances (HOLD) requires neither a priori data from the robot environment, nor a set of task-specific human demonstrations, nor a predefined notion of correspondence across morphologies, yet it is able to accelerate training of several manipulation tasks on a simulated robot arm compared to using only a sparse reward obtained from task completion.
Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing
In this paper, we introduce a new algorithm based on archetypal analysis for blind hyperspectral unmixing, assuming linear mixing of endmembers.
High Dynamic Range and Super-Resolution from Raw Image Bursts
Photographs captured by smartphones and mid-range cameras have limited spatial resolution and dynamic range, with noisy response in underexposed regions and color artefacts in saturated areas.
Self Supervised Learning for Few Shot Hyperspectral Image Classification
Deep learning has proven to be a very effective approach for Hyperspectral Image (HSI) classification.
On the Benefits of Large Learning Rates for Kernel Methods
This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms.
The Spectral Bias of Polynomial Neural Networks
Inspired by such studies, we conduct a spectral analysis of the Neural Tangent Kernel (NTK) of PNNs.
Efficient Kernel UCB for Contextual Bandits
While standard methods require a O(CT^3) complexity where T is the horizon and the constant C is related to optimizing the UCB rule, we propose an efficient contextual algorithm for large-scale problems.
Self-Supervised Models are Continual Learners
Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale.
Amortized Implicit Differentiation for Stochastic Bilevel Optimization
We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex.
A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration
Hyperspectral imaging offers new perspectives for diverse applications, ranging from the monitoring of the environment using airborne or satellite remote sensing, precision farming, food safety, planetary exploration, or astrophysics.
Beyond Tikhonov: Faster Learning with Self-Concordant Losses via Iterative Regularization
The theory of spectral filtering is a remarkable tool to understand the statistical properties of learning with kernels.
Residual Reinforcement Learning from Demonstrations
Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal.
GraphiT: Encoding Graph Structure in Transformers
We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs).
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
This paper reviews the NTIRE2021 challenge on burst super-resolution.
Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularization
The theory of spectral filtering is a remarkable tool to understand the statistical properties of learning with kernels.
Emerging Properties in Self-Supervised Vision Transformers
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).
Ranked #2 on
Copy Detection
on Copydays strong subset
Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts
This presentation addresses the problem of reconstructing a high-resolution image from multiple lower-resolution snapshots captured from slightly different viewpoints in space and time.
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems, and whose architectures are derived from an optimization algorithm.
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range dependencies, and possibly few labeled data.
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much.
Ranked #9 on
Image Classification
on OmniBenchmark
Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline Evaluation
Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare.
Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
Popular approaches for few-shot classification consist of first learning a generic data representation based on a large annotated dataset, before adapting the representation to new classes given only a few labeled samples.
Ranked #4 on
Few-Shot Image Classification
on Meta-Dataset Rank
Convolutional Kernel Networks for Graph-Structured Data
On the other hand, our model can also be trained end-to-end on large-scale data, leading to new types of graph convolutional neural networks.
Pruning Convolutional Neural Networks with Self-Supervision
In this work, we investigate the use of standard pruning methods, developed primarily for supervised learning, for networks trained without labels (i. e. on self-supervised tasks).
Cyanure: An Open-Source Toolbox for Empirical Risk Minimization for Python, C++, and soon more
Cyanure is an open-source C++ software package with a Python interface.
Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
Non-local self-similarity and sparsity principles have proven to be powerful priors for natural image modeling.
Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions
We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees.
Finding Winning Tickets with Limited (or No) Supervision
The lottery ticket hypothesis argues that neural networks contain sparse subnetworks, which, if appropriately initialized (the winning tickets), are capable of matching the accuracy of the full network when trained in isolation.
Recurrent Kernel Networks
Substring kernels are classical tools for representing biological sequences or text.
A Generic Acceleration Framework for Stochastic Composite Optimization
In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex.
On the Inductive Bias of Neural Tangent Kernels
State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties.
Estimate Sequences for Variance-Reduced Stochastic Composite Optimization
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov.
Unsupervised Pre-Training of Image Features on Non-Curated Data
Our goal is to bridge the performance gap between unsupervised methods trained on curated data, which are costly to obtain, and massive raw datasets that are easily available.
Ranked #65 on
Self-Supervised Image Classification
on ImageNet (finetuned)
(using extra training data)
Diversity with Cooperation: Ensemble Methods for Few-Shot Classification
Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples.
Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov.
A Kernel Perspective for Regularizing Deep Neural Networks
We propose a new point of view for regularizing deep neural networks by using the norm of a reproducing kernel Hilbert space (RKHS).
On Regularization and Robustness of Deep Neural Networks
In this work, we study the connection between regularization and robustness of deep neural networks by viewing them as elements of a reproducing kernel Hilbert space (RKHS) of functions and by regularizing them using the RKHS norm.
Extracting representations of cognition across neuroimaging studies improves brain decoding
Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework.
On the Importance of Visual Context for Data Augmentation in Scene Understanding
In this work, we consider object detection, semantic and instance segmentation and augment the training images by blending objects in existing scenes, using instance segmentation annotations.
Modeling Visual Context is Key to Augmenting Object Detection Datasets
For this approach to be successful, we show that modeling appropriately the visual context surrounding objects is crucial to place them in the right environment.
Unsupervised Learning of Artistic Styles with Archetypal Style Analysis
In this paper, we introduce an unsupervised learning approach to automatically discover, summarize, and manipulate artistic styles from large collections of paintings.
Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice
One of the keys to achieve acceleration in theory and in practice is to solve these sub-problems with appropriate accuracy by using the right stopping criterion and the right warm-start strategy.
Invariance and Stability of Deep Convolutional Representations
In this paper, we study deep signal representations that are near-invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information.
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions.
Learning Neural Representations of Human Cognition across Many fMRI Studies
Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets.
BlitzNet: A Real-Time Deep Network for Scene Understanding
Real-time scene understanding has become crucial in many applications such as autonomous driving.
Ranked #2 on
Real-Time Object Detection
on PASCAL VOC 2007
Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations
The success of deep convolutional architectures is often attributed in part to their ability to learn multiscale and invariant representations of natural signals.
Catalyst Acceleration for Gradient-Based Non-Convex Optimization
We introduce a generic scheme to solve nonconvex optimization problems using gradient-based algorithms originally designed for minimizing convex functions.
Stochastic Subsampling for Factorizing Huge Matrices
We present a matrix-factorization algorithm that scales to input matrices with both huge number of rows and columns.
Subsampled online matrix factorization with convergence guarantees
We present a matrix factorization algorithm that scales to input matrices that are large in both dimensions (i. e., that contains morethan 1TB of data).
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure
Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions.
An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration
We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms.
End-to-End Kernel Learning with Supervised Convolutional Kernel Networks
In this paper, we introduce a new image representation based on a multilayer kernel machine.
Dictionary Learning for Massive Matrix Factorization
Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising.
Ranked #12 on
Recommendation Systems
on MovieLens 10M
Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision.
DOLPHIn - Dictionary Learning for Phase Retrieval
We propose a new algorithm to learn a dictionary for reconstructing and sparsely encoding signals from measurements without phase.
Local Convolutional Features With Unsupervised Training for Image Retrieval
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval.
Sparse Modeling for Image and Vision Processing
In recent years, a large amount of multi-disciplinary research has been conducted on sparse models and their applications.
Convolutional Kernel Networks
An important goal in visual recognition is to devise image representations that are invariant to particular transformations.
Ranked #23 on
Image Classification
on MNIST
Mixing Body-Part Sequences for Human Pose Estimation
In this paper, we present a method for estimating articulated human poses in videos.
Fast and Robust Archetypal Analysis for Representation Learning
We revisit a pioneer unsupervised learning technique called archetypal analysis, which is related to successful data analysis methods such as sparse coding and non-negative matrix factorization.
On learning to localize objects with minimal supervision
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain.
Ranked #35 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning
We present convergence guarantees for non-convex and convex optimization when the upper bounds approximate the objective up to a smooth error; we call such upper bounds "first-order surrogate functions".
Stochastic Majorization-Minimization Algorithms for Large-Scale Optimization
Majorization-minimization algorithms consist of iteratively minimizing a majorizing surrogate of an objective function.
Optimization with First-Order Surrogate Functions
In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function.
Supervised Feature Selection in Graphs with Path Coding Penalties and Network Flows
We consider supervised learning problems where the features are embedded in a graph, such as gene expressions in a gene network.
Network Flow Algorithms for Structured Sparsity
Our algorithm scales up to millions of groups and variables, and opens up a whole new range of applications for structured sparse models.
Task-Driven Dictionary Learning
Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience and signal processing.
Supervised Dictionary Learning
It is now well established that sparse signal models are well suited to restoration tasks and can effectively be learned from audio, image, and video data.
