Search Results for author: Isabelle Bloch

Found 35 papers, 9 papers with code

Weakly-supervised positional contrastive learning: application to cirrhosis classification

1 code implementation10 Jul 2023 Emma Sarfati, Alexandre Bône, Marc-Michel Rohé, Pietro Gori, Isabelle Bloch

Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e. g., radiological scores).

Classification Contrastive Learning

Meta-Learners for Few-Shot Weakly-Supervised Medical Image Segmentation

1 code implementation11 May 2023 Hugo Oliveira, Pedro H. T. Gama, Isabelle Bloch, Roberto Marcondes Cesar Jr

Most uses of Meta-Learning in visual recognition are very often applied to image classification, with a relative lack of works in other tasks {such} as segmentation and detection.

Image Classification Image Segmentation +6

Morpho-logic from a Topos Perspective: Application to symbolic AI

no code implementations8 Mar 2023 Marc Aiguier, Isabelle Bloch, Salim Nibouche, Ramon Pino Perez

Then we introduce the notion of structuring neighborhoods, and show that the dilations and erosions based on them lead to a constructive modal logic, for which a sound and complete proof system is proposed.

Model-based inexact graph matching on top of CNNs for semantic scene understanding

1 code implementation18 Jan 2023 Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, Isabelle Bloch

On FASSEG data, results show that our module improves accuracy of the CNN by about 6. 3% (the Hausdorff distance decreases from 22. 11 to 20. 71).

Brain Segmentation Graph Matching +3

Anatomically constrained CT image translation for heterogeneous blood vessel segmentation

no code implementations4 Oct 2022 Giammarco La Barbera, Haithem Boussaid, Francesco Maso, Sabine Sarnacki, Laurence Rouet, Pietro Gori, Isabelle Bloch

Anatomical structures such as blood vessels in contrast-enhanced CT (ceCT) images can be challenging to segment due to the variability in contrast medium diffusion.


Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing

no code implementations28 Jul 2022 Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo, Isabelle Bloch

In discrete signal and image processing, many dilations and erosions can be written as the max-plus and min-plus product of a matrix on a vector.

Optimizing transformations for contrastive learning in a differentiable framework

no code implementations27 Jul 2022 Camille Ruppli, Pietro Gori, Roberto Ardon, Isabelle Bloch

Following previous works that introduce a small amount of supervision, we propose a framework to find optimal transformations for contrastive learning using a differentiable transformation network.

Contrastive Learning

Is the U-Net Directional-Relationship Aware?

1 code implementation6 Jul 2022 Mateus Riva, Pietro Gori, Florian Yger, Isabelle Bloch

CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field.


Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers

no code implementations12 May 2022 Robin Kips, Ruowei Jiang, Sileye Ba, Brendan Duke, Matthieu Perrot, Pietro Gori, Isabelle Bloch

In this paper we propose a novel framework based on deep learning to build a real-time inverse graphics encoder that learns to map a single example image into the parameter space of a given augmented reality rendering engine.

Neural Rendering Self-Supervised Learning +1

Hair Color Digitization through Imaging and Deep Inverse Graphics

no code implementations8 Feb 2022 Robin Kips, Panagiotis-Alexandros Bokaris, Matthieu Perrot, Pietro Gori, Isabelle Bloch

Since rendering realistic hair images requires path-tracing rendering, the conventional inverse graphics approach based on differentiable rendering is untractable.

A deep residual learning implementation of Metamorphosis

no code implementations1 Feb 2022 Matthis Maillard, Anton François, Joan Glaunès, Isabelle Bloch, Pietro Gori

In medical imaging, most of the image registration methods implicitly assume a one-to-one correspondence between the source and target images (i. e., diffeomorphism).

Image Registration

Template-Based Graph Clustering

1 code implementation5 Jul 2021 Mateus Riva, Florian Yger, Pietro Gori, Roberto M. Cesar Jr., Isabelle Bloch

We propose a novel graph clustering method guided by additional information on the underlying structure of the clusters (or communities).

Clustering Graph Clustering

Knowledge distillation from multi-modal to mono-modal segmentation networks

no code implementations17 Jun 2021 Minhao Hu, Matthis Maillard, Ya zhang, Tommaso Ciceri, Giammarco La Barbera, Isabelle Bloch, Pietro Gori

In this paper, we propose KD-Net, a framework to transfer knowledge from a trained multi-modal network (teacher) to a mono-modal one (student).

Brain Tumor Segmentation Image Segmentation +3

Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example

no code implementations12 May 2021 Robin Kips, Ruowei Jiang, Sileye Ba, Edmund Phung, Parham Aarabi, Pietro Gori, Matthieu Perrot, Isabelle Bloch

While makeup virtual-try-on is now widespread, parametrizing a computer graphics rendering engine for synthesizing images of a given cosmetics product remains a challenging task.

Virtual Try-on

Approximation of dilation-based spatial relations to add structural constraints in neural networks

no code implementations22 Feb 2021 Mateus Riva, Pietro Gori, Florian Yger, Roberto Cesar, Isabelle Bloch

Several relations can be modeled as a morphological dilation of a reference object with a structuring element representing the semantics of the relation, from which the degree of satisfaction of the relation between another object and the reference object can be derived.

Object Object Recognition +1

Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification

2 code implementations4 Dec 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks.

Bayesian Inference Decision Making Under Uncertainty +5

Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations

no code implementations29 Sep 2020 Antoine Pirovano, Hippolyte Heuberger, Sylvain Berlemont, Saïd Ladjal, Isabelle Bloch

We formalize the design of WSI classification architectures and propose a piece-wise interpretability approach, relying on gradient-based methods, feature visualization and multiple instance learning context.

Classification General Classification +2

CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer

no code implementations24 Aug 2020 Robin Kips, Pietro Gori, Matthieu Perrot, Isabelle Bloch

While existing makeup style transfer models perform an image synthesis whose results cannot be explicitly controlled, the ability to modify makeup color continuously is a desirable property for virtual try-on applications.

Attribute Image Generation +3

One Versus all for deep Neural Network Incertitude (OVNNI) quantification

no code implementations1 Jun 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.

Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques

no code implementations20 Mar 2020 Qinkai Zheng, Han Qiu, Gerard Memmi, Isabelle Bloch

This report is about applications based on spatial-frequency transform and deep learning techniques.


TRADI: Tracking deep neural network weight distributions for uncertainty estimation

no code implementations ECCV 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function.

Computational Efficiency General Classification +2

Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks

1 code implementation19 Mar 2019 Yunxiang Zhang, Samy Blusseau, Santiago Velasco-Forero, Isabelle Bloch, Jesus Angulo

Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they behave when incorporated in layers of conventional neural networks.

Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction

no code implementations5 Mar 2018 Marc Aiguier, Jamal Atif, Isabelle Bloch, Ramón Pino-Pérez

The aim of this paper is to introduce a new framework for defining abductive reasoning operators based on a notion of retraction in arbitrary logics defined as satisfaction systems.

Morphologic for knowledge dynamics: revision, fusion, abduction

no code implementations14 Feb 2018 Isabelle Bloch, Jérôme Lang, Ramón Pino Pérez, Carlos Uzcátegui

Several tasks in artificial intelligence require to be able to find models about knowledge dynamics.

Classification of MRI data using Deep Learning and Gaussian Process-based Model Selection

no code implementations16 Jan 2017 Hadrien Bertrand, Matthieu Perrot, Roberto Ardon, Isabelle Bloch

Improving the model is not an easy task, due to the large number of hyper-parameters governing both the architecture and the training of the network, and to the limited understanding of their relevance.

Gaussian Processes General Classification +1

Exploring Structure for Long-Term Tracking of Multiple Objects in Sports Videos

1 code implementation19 Dec 2016 Henrique Morimitsu, Isabelle Bloch, Roberto M. Cesar-Jr

In this paper, we propose a novel approach for exploiting structural relations to track multiple objects that may undergo long-term occlusion and abrupt motion.

Relaxation-based revision operators in description logics

no code implementations26 Feb 2015 Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot

In this paper we address both the generalization of the well-known AGM postulates, and the definition of concrete and well-founded revision operators in different DL families.


Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics

no code implementations8 Feb 2015 Marc Aiguier, Jamal Atif, Isabelle Bloch, Céline Hudelot

Belief revision of knowledge bases represented by a set of sentences in a given logic has been extensively studied but for specific logics, mainly propositional, and also recently Horn and description logics.

Cannot find the paper you are looking for? You can Submit a new open access paper.