Counterfactual Image Generation for adversarially robust and interpretable Classifiers

no code implementations • 1 Oct 2023 • Rafael Bischof, Florian Scheidegger, Michael A. Kraus, A. Cristiano I. Malossi

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks.

counterfactual Descriptive +2

MAEDAY: MAE for few and zero shot AnomalY-Detection

1 code implementation • 25 Nov 2022 • Eli Schwartz, Assaf Arbelle, Leonid Karlinsky, Sivan Harary, Florian Scheidegger, Sivan Doveh, Raja Giryes

We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD).

Anomaly Detection Image Inpainting +4

Generating Efficient DNN-Ensembles with Evolutionary Computation

no code implementations • 18 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

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

no code implementations • NeurIPS 2019 • Florian Scheidegger, Luca Benini, Costas Bekas, A. Cristiano I. Malossi

The narrow-space search of floating-point models improves the accuracy on CIFAR10 of an established IoT model from 70. 64% to 74. 87% within the same memory constraints.

General Classification Image Classification

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

no code implementations • 24 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

PAGAN: Portfolio Analysis with Generative Adversarial Networks

no code implementations • 19 Sep 2019 • Giovanni Mariani, Yada Zhu, Jianbo Li, Florian Scheidegger, Roxana Istrate, Costas Bekas, A. Cristiano I. Malossi

Sound financial theories demonstrate that in an efficient marketplace all information available today, including expectations on future events, are represented in today prices whereas future price trend is driven by the uncertainty.

Computational Finance Statistical Finance

NeuNetS: An Automated Synthesis Engine for Neural Network Design

no code implementations • 17 Jan 2019 • Atin Sood, Benjamin Elder, Benjamin Herta, Chao Xue, Costas Bekas, A. Cristiano I. Malossi, Debashish Saha, Florian Scheidegger, Ganesh Venkataraman, Gegi Thomas, Giovanni Mariani, Hendrik Strobelt, Horst Samulowitz, Martin Wistuba, Matteo Manica, Mihir Choudhury, Rong Yan, Roxana Istrate, Ruchir Puri, Tejaswini Pedapati

Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice.

BAGAN: Data Augmentation with Balancing GAN

4 code implementations • 26 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

Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy

1 code implementation • 26 Mar 2018 • Florian Scheidegger, Roxana Istrate, Giovanni Mariani, Luca Benini, Costas Bekas, Cristiano Malossi

In the deep-learning community new algorithms are published at an incredible pace.

General Classification Image Classification