Search Results for author:
Found 30 papers, 10 papers with code
FLIM-based Salient Object Detection Networks with Adaptive Decoders
We compare FLIM models with adaptive decoders for two challenging SOD tasks with three lightweight networks from the state-of-the-art, two FLIM networks with decoders trained by backpropagation, and one FLIM network whose labeled markers define the decoder's weights.
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos.
Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation
The significant size differences among various organs in the human body lead to imbalanced class distribution, which is a major challenge in the real-world application of these SSL approaches.
Evolutionary Retrofitting
AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying non-differentiable optimization, including evolutionary methods, to refine fully-trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set.
Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
We apply the log-normal method to the attack of fake detectors, and get successful attacks: importantly, these attacks are not detected by detectors specialized on classical adversarial attacks.
Reasoning with trees: interpreting CNNs using hierarchies
We introduce a framework that uses hierarchical segmentation techniques for faithful and interpretable explanations of Convolutional Neural Networks (CNNs).
Quantile Activation: Correcting a Failure Mode of ML Models
In this article, we propose a simple activation function, quantile activation (QACT), that addresses this problem without significantly increasing computational costs.
Learning and Leveraging World Models in Visual Representation Learning
Joint-Embedding Predictive Architecture (JEPA) has emerged as a promising self-supervised approach that learns by leveraging a world model.
A Novel Approach to Regularising 1NN classifier for Improved Generalization
In this paper, we propose a class of non-parametric classifiers, that learn arbitrary boundaries and generalize well.
Clustering Dynamics for Improved Speed Prediction Deriving from Topographical GPS Registrations
A persistent challenge in the field of Intelligent Transportation Systems is to extract accurate traffic insights from geographic regions with scarce or no data coverage.
Bridging Human Concepts and Computer Vision for Explainable Face Verification
With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions.
Transforming gradient-based techniques into interpretable methods
The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation.
Dual Structure-Aware Image Filterings for Semi-supervised Medical Image Segmentation
In this paper, we propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation.
PrivacyGAN: robust generative image privacy
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications.
Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation
Latent diffusion models excel at producing high-quality images from text.
SWMLP: Shared Weight Multilayer Perceptron for Car Trajectory Speed Prediction using Road Topographical Features
One concern is that, although there are studies that give good results for these data, the data from these regions may not be sufficiently representative to describe all the traffic patterns in the rest of the world.
Unsupervised discovery of Interpretable Visual Concepts
Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a visualization technique containing a high level of information, but with difficult interpretation.
Self-supervised learning of Split Invariant Equivariant representations
We hope that both our introduced dataset and approach will enable learning richer representations without supervision in more complex scenarios.
Fairness in generative modeling
We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling.
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
Joint-Embedding Self Supervised Learning (JE-SSL) has seen a rapid development, with the emergence of many method variations but only few principled guidelines that would help practitioners to successfully deploy them.
On the duality between contrastive and non-contrastive self-supervised learning
Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and non-contrastive approaches.
Some equivalence relation between persistent homology and morphological dynamics
In Mathematical Morphology (MM), connected filters based on dynamics are used to filter the extrema of an image.
Assessing hierarchies by their consistent segmentations
We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy elements, and that representing a segmentation with only a few hierarchy elements is often possible.
Triplet-Watershed for Hyperspectral Image Classification
In this article, we propose to use a watershed classifier.
Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder
Motivation: Single cell RNA sequencing (scRNA-seq) data makes studying the development of cells possible at unparalleled resolution.
Rethinking Interactive Image Segmentation: Feature Space Annotation
This strategy is in stark contrast to existing interactive segmentation methodologies, which perform annotation in the image domain.
VOIDD: automatic vessel of intervention dynamic detection in PCI procedures
We present the automatic VOIDD algorithm to detect the vessel of intervention which is going to be treated during the procedure by combining information from the vessel image with contrast agent injection and images acquired during guidewire tip navigation.
Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selection
Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford-Shah functional.
New characterizations of minimum spanning trees and of saliency maps based on quasi-flat zones
We study three representations of hierarchies of partitions: dendrograms (direct representations), saliency maps, and minimum spanning trees.
A graph-based mathematical morphology reader
This survey paper aims at providing a "literary" anthology of mathematical morphology on graphs.
