Search Results for author: Cristiano Malossi

Found 8 papers, 3 papers with code

Active Learning for Imbalanced Civil Infrastructure Data

no code implementations19 Oct 2022 Thomas Frick, Diego Antognini, Mattia Rigotti, Ioana Giurgiu, Benjamin Grewe, Cristiano Malossi

Unfortunately, annotation costs are incredibly high as our proprietary civil engineering dataset must be annotated by highly trained engineers.

Active Learning

Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures

no code implementations22 Sep 2022 Klara Janouskova, Mattia Rigotti, Ioana Giurgiu, Cristiano Malossi

These are used within an assisted labeling framework where the annotators can interact with them as proposal segmentation masks by deciding to accept, reject or modify them, and interactions are logged as weak labels to further refine the classifier.

Enabling Reproducibility and Meta-learning Through a Lifelong Database of Experiments (LDE)

no code implementations22 Feb 2022 Jason Tsay, Andrea Bartezzaghi, Aleke Nolte, Cristiano Malossi

We present the Lifelong Database of Experiments (LDE) that automatically extracts and stores linked metadata from experiment artifacts and provides features to reproduce these artifacts and perform meta-learning across them.


Generating Efficient DNN-Ensembles with Evolutionary Computation

no code implementations18 Sep 2020 Marc Ortiz, Florian Scheidegger, Marc Casas, Cristiano Malossi, Eduard Ayguadé

In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models.

Ensemble Learning Image Classification

Reducing Data Motion to Accelerate the Training of Deep Neural Networks

1 code implementation5 Apr 2020 Sicong Zhuang, Cristiano Malossi, Marc Casas

This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices.

Distributed, Parallel, and Cluster Computing

Constrained deep neural network architecture search for IoT devices accounting hardware calibration

no code implementations24 Sep 2019 Florian Scheidegger, Luca Benini, Costas Bekas, Cristiano Malossi

We further improve the accuracy to 82. 07% by including 16-bit half types and we obtain the best accuracy of 83. 45% by extending the search with model optimized IEEE 754 reduced types.

General Classification Image Classification

BAGAN: Data Augmentation with Balancing GAN

4 code implementations26 Mar 2018 Giovanni Mariani, Florian Scheidegger, Roxana Istrate, Costas Bekas, Cristiano Malossi

The generator in the GAN is initialized with the encoder module of an autoencoder that enables us to learn an accurate class-conditioning in the latent space.

Data Augmentation Image Classification

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