Search Results for author: Paolo Favaro

Found 46 papers, 12 papers with code

Learning Video Representations by Transforming Time

no code implementations ECCV 2020 Simon Jenni, Givi Meishvili, Paolo Favaro

Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, which require to accurately distinguish the motion of objects.

Action Recognition Self-Supervised Learning

Semi-supervised Vision Transformers at Scale

no code implementations11 Aug 2022 Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang, Davide Modolo, Rahul Bhotika, Zhuowen Tu, Stefano Soatto

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks.

Inductive Bias

Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning

no code implementations27 Jul 2022 Abdelhak Lemkhenter, Paolo Favaro

In this work we introduce a novel meta-learning method for sleep scoring based on self-supervised learning.

Meta-Learning Self-Supervised Learning

Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring

no code implementations5 Jul 2022 Luigi Fiorillo, Davide Pedroncelli, Valentina Agostini, Paolo Favaro, Francesca Dalia Faraci

In this study, we aim to insert the multiple-knowledge of the different physicians into the training procedure. The goal is to optimize a model training, exploiting the full information that can be extracted from the consensus of a group of scorers.

Controllable Video Generation through Global and Local Motion Dynamics

no code implementations13 Apr 2022 Aram Davtyan, Paolo Favaro

We present GLASS, a method for Global and Local Action-driven Sequence Synthesis.

Video Generation

DILEMMA: Self-Supervised Shape and Texture Learning with Transformers

no code implementations10 Apr 2022 Sepehr Sameni, Simon Jenni, Paolo Favaro

To retain texture discrimination, the ViT is also trained as in MoCo with a student-teacher architecture and a contrastive loss over an extra learnable class token.

Ranked #86 on Image Classification on ObjectNet (using extra training data)

Image Classification Self-Supervised Learning

Learning to Deblur and Rotate Motion-Blurred Faces

no code implementations14 Dec 2021 Givi Meishvili, Attila Szabó, Simon Jenni, Paolo Favaro

Our method handles the complexity of face blur by implicitly learning the geometry and motion of faces through the joint training on three large datasets: FFHQ and 300VW, which are publicly available, and a new Bern Multi-View Face Dataset (BMFD) that we built.

DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model with Uncertainty Estimates

no code implementations24 Aug 2021 Luigi Fiorillo, Paolo Favaro, Francesca Dalia Faraci

We exploit, for the first time in sleep scoring, the Monte Carlo dropout technique to enhance the performance of the architecture and to also detect the uncertain instances.


Generative Adversarial Learning via Kernel Density Discrimination

no code implementations13 Jul 2021 Abdelhak Lemkhenter, Adam Bielski, Alp Eren Sari, Paolo Favaro

We show a boost in the quality of generated samples with respect to FID from 10% to 40% compared to the baseline.

Contrastive Learning

KOALA: A Kalman Optimization Algorithm with Loss Adaptivity

no code implementations7 Jul 2021 Aram Davtyan, Sepehr Sameni, Llukman Cerkezi, Givi Meishvilli, Adam Bielski, Paolo Favaro

Moreover, we show that the Kalman Filter dynamical model for the evolution of the unknown parameters can be used to capture the gradient dynamics of advanced methods such as Momentum and Adam.

Language Modelling Stochastic Optimization

A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention

no code implementations18 Jun 2021 Tomoki Watanabe, Paolo Favaro

However, because the classifier might still make mistakes, especially at the beginning of the training, we also refine the labels through self-attention, by using the labeling of real data samples only when the classifier outputs a high classification probability score.

Optical Flow Dataset Synthesis from Unpaired Images

no code implementations2 Apr 2021 Adrian Wälchli, Paolo Favaro

In the case of synthetic data, the ground truth provides an exact and explicit description of what optical flow to assign to a given scene.

Optical Flow Estimation

ISD: Self-Supervised Learning by Iterative Similarity Distillation

1 code implementation ICCV 2021 Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Vipin Pillai, Paolo Favaro, Hamed Pirsiavash

Hence, we introduce a self supervised learning algorithm where we use a soft similarity for the negative images rather than a binary distinction between positive and negative pairs.

Contrastive Learning Self-Supervised Learning +1

Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimation

no code implementations13 Oct 2020 Simon Jenni, Paolo Favaro

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses.

3D Pose Estimation Monocular 3D Human Pose Estimation +1

Boosting Generalization in Bio-Signal Classification by Learning the Phase-Amplitude Coupling

1 code implementation16 Sep 2020 Abdelhak Lemkhenter, Paolo Favaro

Various hand-crafted features representations of bio-signals rely primarily on the amplitude or power of the signal in specific frequency bands.

General Classification Self-Supervised Learning

Video Representation Learning by Recognizing Temporal Transformations

no code implementations21 Jul 2020 Simon Jenni, Givi Meishvili, Paolo Favaro

Our representations can be learned from data without human annotation and provide a substantial boost to the training of neural networks on small labeled data sets for tasks such as action recognition, which require to accurately distinguish the motion of objects.

Action Recognition Representation Learning +1

Learning to Model and Calibrate Optics via a Differentiable Wave Optics Simulator

1 code implementation18 May 2020 Josue Page, Paolo Favaro

We present a novel learning-based method to build a differentiable computational model of a real fluorescence microscope.

Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics

no code implementations CVPR 2020 Simon Jenni, Hailin Jin, Paolo Favaro

Based on this criterion, we introduce a novel image transformation that we call limited context inpainting (LCI).

Learning to Reconstruct Confocal Microscopy Stacks from Single Light Field Images

1 code implementation24 Mar 2020 Josue Page, Federico Saltarin, Yury Belyaev, Ruth Lyck, Paolo Favaro

To train our network, we built a data set of 362 light field images of mouse brain blood vessels and the corresponding aligned set of 3D confocal scans, which we use as ground truth.

Unsupervised Generative 3D Shape Learning from Natural Images

no code implementations1 Oct 2019 Attila Szabó, Givi Meishvili, Paolo Favaro

In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way.

Image Generation

Learning to Have an Ear for Face Super-Resolution

no code implementations CVPR 2020 Givi Meishvili, Simon Jenni, Paolo Favaro

To combine the aural and visual modalities, we propose a method to first build the latent representations of a face from the lone audio track and then from the lone low-resolution image.

Audio Super-Resolution Face Reconstruction +2

On Stabilizing Generative Adversarial Training with Noise

no code implementations CVPR 2019 Simon Jenni, Paolo Favaro

We notice that the distributions of real and generated data should match even when they undergo the same filtering.

Emergence of Object Segmentation in Perturbed Generative Models

1 code implementation NeurIPS 2019 Adam Bielski, Paolo Favaro

To force the generator to learn a representation where the foreground layer corresponds to an object, we perturb the output of the generative model by introducing a random shift of both the foreground image and mask relative to the background.

Semantic Segmentation Unsupervised Object Segmentation

Smart, Deep Copy-Paste

no code implementations15 Mar 2019 Tiziano Portenier, Qiyang Hu, Paolo Favaro, Matthias Zwicker

In this work, we propose a novel system for smart copy-paste, enabling the synthesis of high-quality results given a masked source image content and a target image context as input.

Learning to Take Directions One Step at a Time

1 code implementation5 Dec 2018 Qiyang Hu, Adrian Wälchli, Tiziano Portenier, Matthias Zwicker, Paolo Favaro

Because items in an image can be animated in arbitrarily many different ways, we introduce as control signal a sequence of motion strokes.

Video Prediction

Unsupervised 3D Shape Learning from Image Collections in the Wild

no code implementations26 Nov 2018 Attila Szabó, Paolo Favaro

To achieve realism, the generative model is trained adversarially against a discriminator that tries to distinguish between the output of the renderer and real images from the given data set.

Deep Bilevel Learning

1 code implementation ECCV 2018 Simon Jenni, Paolo Favaro

Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting.

Bilevel Optimization

Understanding Degeneracies and Ambiguities in Attribute Transfer

no code implementations ECCV 2018 Attila Szabo, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro

We study the problem of building models that can transfer selected attributes from one image to another without affecting the other attributes.

Normalized Blind Deconvolution

no code implementations ECCV 2018 Meiguang Jin, Stefan Roth, Paolo Favaro

We introduce a family of novel approaches to single-image blind deconvolution, ie , the problem of recovering a sharp image and a blur kernel from a single blurry input.

Self-Supervised Feature Learning by Learning to Spot Artifacts

no code implementations CVPR 2018 Simon Jenni, Paolo Favaro

To generate images with artifacts, we pre-train a high-capacity autoencoder and then we use a damage and repair strategy: First, we freeze the autoencoder and damage the output of the encoder by randomly dropping its entries.

Self-Supervised Learning

Boosting Self-Supervised Learning via Knowledge Transfer

no code implementations CVPR 2018 Mehdi Noroozi, Ananth Vinjimoor, Paolo Favaro, Hamed Pirsiavash

We use this framework to design a novel self-supervised task, which achieves state-of-the-art performance on the common benchmarks in PASCAL VOC 2007, ILSVRC12 and Places by a significant margin.

object-detection Object Detection +2

FaceShop: Deep Sketch-based Face Image Editing

no code implementations24 Apr 2018 Tiziano Portenier, Qiyang Hu, Attila Szabó, Siavash Arjomand Bigdeli, Paolo Favaro, Matthias Zwicker

We present a novel system for sketch-based face image editing, enabling users to edit images intuitively by sketching a few strokes on a region of interest.

Image Manipulation

Motion deblurring of faces

no code implementations8 Mar 2018 Grigorios G. Chrysos, Paolo Favaro, Stefanos Zafeiriou

Notwithstanding, a much less standing mode of variation is motion deblurring, which however presents substantial challenges in face analysis.

Deblurring Face Verification

Disentangling Factors of Variation by Mixing Them

no code implementations CVPR 2018 Qiyang Hu, Attila Szabó, Tiziano Portenier, Matthias Zwicker, Paolo Favaro

We learn our representation without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively; second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding degenerate feature mappings where some chunks are completely ignored.

General Classification

Challenges in Disentangling Independent Factors of Variation

2 code implementations ICLR 2018 Attila Szabó, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro

Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis.

Image Generation

Reflection Separation and Deblurring of Plenoptic Images

no code implementations22 Aug 2017 Paramanand Chandramouli, Mehdi Noroozi, Paolo Favaro

In this paper, we address the problem of reflection removal and deblurring from a single image captured by a plenoptic camera.

Deblurring Depth Estimation +1

Noise-Blind Image Deblurring

no code implementations CVPR 2017 Meiguang Jin, Stefan Roth, Paolo Favaro

We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level.

Blind Image Deblurring Image Deblurring

Motion Deblurring in the Wild

no code implementations5 Jan 2017 Mehdi Noroozi, Paramanand Chandramouli, Paolo Favaro

The task of image deblurring is a very ill-posed problem as both the image and the blur are unknown.

Deblurring Image Deblurring

Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles

7 code implementations30 Mar 2016 Mehdi Noroozi, Paolo Favaro

By following the principles of self-supervision, we build a convolutional neural network (CNN) that can be trained to solve Jigsaw puzzles as a pretext task, which requires no manual labeling, and then later repurposed to solve object classification and detection.

Representation Learning Transfer Learning

A Clearer Picture of Blind Deconvolution

no code implementations30 Nov 2014 Daniele Perrone, Paolo Favaro

Our analysis reveals the very reason why an algorithm based on total variation works.

Motion Deblurring for Plenoptic Images

no code implementations16 Aug 2014 Paramanand Chandramouli, Paolo Favaro, Daniele Perrone

We address for the first time the issue of motion blur in light field images captured from plenoptic cameras.


Total Variation Blind Deconvolution: The Devil is in the Details

no code implementations CVPR 2014 Daniele Perrone, Paolo Favaro

This then results in a procedure that eludes the no-blur solution, despite it being a global minimum of the original energy.

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