Search Results for author:
Found 35 papers, 8 papers with code
Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics
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.
Relaxation-based revision operators in description logics
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.
Exploring Structure for Long-Term Tracking of Multiple Objects in Sports Videos
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.
Classification of MRI data using Deep Learning and Gaussian Process-based Model Selection
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.
Morphologic for knowledge dynamics: revision, fusion, abduction
Several tasks in artificial intelligence require to be able to find models about knowledge dynamics.
Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction
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.
Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks
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.
Part-based approximations for morphological operators using asymmetric auto-encoders
This paper addresses the issue of building a part-based representation of a dataset of images.
TRADI: Tracking deep neural network weight distributions for uncertainty estimation
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.
Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
This report is about applications based on spatial-frequency transform and deep learning techniques.
One Versus all for deep Neural Network Incertitude (OVNNI) quantification
This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.
CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer
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.
Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations
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.
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification
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.
Ranked #132 on
Image Classification
on CIFAR-10
Comparing Deep Learning strategies for paired but unregistered multimodal segmentation of the liver in T1 and T2-weighted MRI
We address the problem of multimodal liver segmentation in paired but unregistered T1 and T2-weighted MR images.
Approximation of dilation-based spatial relations to add structural constraints in neural networks
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.
Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example
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.
Knowledge distillation from multi-modal to mono-modal segmentation networks
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).
Template-Based Graph Clustering
We propose a novel graph clustering method guided by additional information on the underlying structure of the clusters (or communities).
Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation
Due to a high heterogeneity in pose and size and to a limited number of available data, segmentation of pediatric images is challenging for deep learning methods.
A deep residual learning implementation of Metamorphosis
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).
Hair Color Digitization through Imaging and Deep Inverse Graphics
Since rendering realistic hair images requires path-tracing rendering, the conventional inverse graphics approach based on differentiable rendering is untractable.
Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
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.
Is the U-Net Directional-Relationship Aware?
CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field.
Optimizing transformations for contrastive learning in a differentiable framework
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.
Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing
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.
Anatomically constrained CT image translation for heterogeneous blood vessel segmentation
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.
Learning shape distributions from large databases of healthy organs: applications to zero-shot and few-shot abnormal pancreas detection
We propose a scalable and data-driven approach to learn shape distributions from large databases of healthy organs.
Model-based inexact graph matching on top of CNNs for semantic scene understanding
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).
Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies
Identifying cirrhosis is key to correctly assess the health of the liver.
Morpho-logic from a Topos Perspective: Application to symbolic AI
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.
Meta-Learners for Few-Shot Weakly-Supervised Medical Image Segmentation
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.
Weakly-supervised positional contrastive learning: application to cirrhosis classification
Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e. g., radiological scores).
Decoupled conditional contrastive learning with variable metadata for prostate lesion detection
Early diagnosis of prostate cancer is crucial for efficient treatment.
Non-Redundant Combination of Hand-Crafted and Deep Learning Radiomics: Application to the Early Detection of Pancreatic Cancer
We address the problem of learning Deep Learning Radiomics (DLR) that are not redundant with Hand-Crafted Radiomics (HCR).
