Scale-Adaptive Superpixels

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, which can be either in the form of a ...

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high ...

Volume electron microscopy is the method of choice for the in situ interrogation of cellular ultrastructure at the nanometer scale, and with the increase in large raw image datasets generated, improving computational strategies for image segmentation and s ...

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

We employ a novel discrete element method (DEM) force formulation to simulate adhesive wear and assess the effects of material and loading parameters on the properties of the third-body layer (TBL) formed during sliding motion. The study emphasizes the rol ...

Stable and uniform beams with low divergence are required in particle accelerators; therefore, beyond the accelerated current, measuring the beam current spatial uniformity and stability over time is necessary to assess the beam performance, since these pa ...

The ITER Heating Neutral Beam (HNB) source prototype SPIDER (Source for the Production of Ions of Deuterium Extracted from a Radio frequency plasma), hosted at the Neutral Beam Test Facility (NBTF) in Padova, Italy, has recently started operating with evap ...

There is a growing recognition that electronic band structure is a local property of materials and devices, and there is steep growth in capabilities to collect the relevant data. New photon sources, from small-laboratory-based lasers to free electron lase ...

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

A good knowledge of material properties is a critical aspect for modeling high-temperature superconductor (HTS) devices. However, the electrical resistivity of coated conductors above the critical current is limited. The major challenge in characterizing t ...

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB ...

The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research com ...

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

Determining the relationship between the cause of damage and the subsequent structural behavior of infrastructure systems requires an accurate characterization of the propagation of cracks, which represents the evolution of the damage state. When no inform ...

This paper reports world averages of measurements of b-hadron, c-hadron, and tau-lepton properties obtained by the Heavy Flavour Averaging Group using results available through September 2018. In rare cases, significant results obtained several months late ...

This paper describes a pipeline for automatically generating level of detail (LOD) models (digital twins), specifically LOD2 and LOD3, from free-standing buildings. Our approach combines structure from motion (SfM) with deep-learning-based segmentation tec ...

Human-centered scene understanding is the process of perceiving and analysing a dynamic scene observed through a network of sensors with emphasis on human-related activities. It includes the visual perception of human-related activities from either single ...

In return strokes, the parameters that can be measured are the channel base current and the return stroke speed. For this reason, many return stroke models have been developed with these two parameters, among others, as inputs. Here, we concentrate on the ...

In this paper, the impact of an increasing number of arbitrary electrical/electronic devices on the overall radiated emissions is investigated. Understanding and quantifying such an impact are prerequisites to the proper evaluation of electromagnetic compa ...

Scale-Adaptive Superpixels

Chat with Graph Search

Deep Active Latent Surfaces for Medical Geometries

Enhancing skin lesion classification: a CNN approach with human baseline comparison

Modular segmentation, spatial analysis and visualization of volume electron microscopy datasets

Detecting Anomalies and Obstacles in Road Scenes

Role of Minimum Adhesive Wear Particle Size in Third-Body Layer Properties

Design and Development of a Diagnostic System for a Non-Intercepting Direct Measure of the SPIDER Ion Source Beamlet Current

Beam homogeneity of caesium seeded SPIDER using a direct beamlet current measurement

Transfer learning application of self-supervised learning in ARPES

Confidence Matters: Applications to Semantic Segmentation

Optimization Method for Extracting Stabilizer Geometry and Properties of REBCO Tapes

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Latent Space Slicing for Enhanced Entropy Modeling in Learning-Based Point Cloud Geometry Compression

Counting People by Estimating People Flows

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Determining crack kinematics from imaged crack patterns

Averages of b-hadron, c-hadron, and tau-lepton properties as of 2018 Heavy Flavor Averaging Group (HFLAV)

Generating LOD3 building models from structure-from-motion and semantic segmentation

Human-Centered Scene Understanding via Crowd Counting

Modified Transmission Line Model with a Current Attenuation Function Derived from the Lightning Radiation Field—MTLD Model

EMC Impact of Disturbances Generated by Multiple Sources