108 citations · 587 across the 36 of their papers we have counts for
43 papers
NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
Loick Chambon, Paul Couairon, Eloi Zablocki +3
Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off:…
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
Sophia Sirko-Galouchenko, Spyros Gidaris, Antonin Vobecky +2
We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understan…
JAFAR: Jack up Any Feature at Any Resolution
Paul Couairon, Loick Chambon, Louis Serrano +3
Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to pro…
Hierarchical Clustering in Mean-Field Coupled Stuart-Landau Oscillators
Nicolas Thomé, Matthias Wolfrum, Katharina Krischer
Clustered solutions in oscillator networks provide an important insight into how a system might diversify from a synchronous solution into spatiotemporal complex solutions. They ca…
DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
Paul Couairon, Mustafa Shukor, Jean-Emmanuel Haugeard +2
Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmen…
Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks
Denis Coquenet, Clément Rambour, Emanuele Dalsasso +1
Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they st…
VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing
Paul Couairon, Clément Rambour, Jean-Emmanuel Haugeard +1
Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, existing diffusion-based video editing approaches lack the a…
Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection
Marc Lafon, Elias Ramzi, Clément Rambour +1
Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method…
Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers
Steeven Janny, Aurélien Béneteau, Madiha Nadri +3
Estimating fluid dynamics is classically done through the simulation and integration of numerical models solving the Navier-Stokes equations, which is computationally complex and t…
Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints
Laura Calem, Hedi Ben-Younes, Patrick Pérez +1
Predicting multiple trajectories for road users is important for automated driving systems: ego-vehicle motion planning indeed requires a clear view of the possible motions of the…
Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation
Loic Themyr, Clement Rambour, Nicolas Thome +2
Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention an…
Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval
Mustafa Shukor, Nicolas Thome, Matthieu Cord
Vision-Language Pretraining (VLP) and Foundation models have been the go-to recipe for achieving SoTA performance on general benchmarks. However, leveraging these powerful techniqu…
Memory transformers for full context and high-resolution 3D Medical Segmentation
Loic Themyr, Clément Rambour, Nicolas Thome +2
Transformer models achieve state-of-the-art results for image segmentation. However, achieving long-range attention, necessary to capture global context, with high-resolution 3D im…
Take One Gram of Neural Features, Get Enhanced Group Robustness
Simon Roburin, Charles Corbière, Gilles Puy +4
Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correl…
Hierarchical Average Precision Training for Pertinent Image Retrieval
Elias Ramzi, Nicolas Audebert, Nicolas Thome +2
Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity. This…
Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction
Vincent Le Guen, Clément Rambour, Nicolas Thome
State-of-the-art methods for optical flow estimation rely on deep learning, which require complex sequential training schemes to reach optimal performances on real-world data. In t…
Swapping Semantic Contents for Mixing Images
Rémy Sun, Clément Masson, Gilles Hénaff +2
Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bot…
Towards efficient feature sharing in MIMO architectures
Rémy Sun, Alexandre Ramé, Clément Masson +2
Multi-input multi-output architectures propose to train multiple subnetworks within one base network and then average the subnetwork predictions to benefit from ensembling for free…
Robust and Decomposable Average Precision for Image Retrieval
Elias Ramzi, Nicolas Thome, Clément Rambour +2
In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP). In this paper, we introduce a method for robust and decomposable average precisi…
Deep Time Series Forecasting with Shape and Temporal Criteria
Vincent Le Guen, Nicolas Thome
This paper addresses the problem of multi-step time series forecasting for non-stationary signals that can present sudden changes. Current state-of-the-art deep learning forecastin…
U-Net Transformer: Self and Cross Attention for Medical Image Segmentation
Olivier Petit, Nicolas Thome, Clément Rambour +1
Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures. In this paper, we introduce the U-Transformer network, which combine…
Confidence Estimation via Auxiliary Models
Charles Corbière, Nicolas Thome, Antoine Saporta +3
Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper…
Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity
Vincent Le Guen, Nicolas Thome
Probabilistic forecasting consists in predicting a distribution of possible future outcomes. In this paper, we address this problem for non-stationary time series, which is very ch…
Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
Yuan Yin, Vincent Le Guen, Jérémie Dona +4
Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purel…