155 citations · 669 across the 21 of their papers we have counts for
27 papers
Cross-Domain Object Detection Using Unsupervised Image Translation
Vinicius F. Arruda, Rodrigo F. Berriel, Thiago M. Paixão +4
Unsupervised domain adaptation for object detection addresses the adaption of detectors trained in a source domain to work accurately in an unseen target domain. Recently, methods…
Budget-Aware Pruning: Handling Multiple Domains with Less Parameters
Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos +2
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant…
Budget-Aware Pruning for Multi-Domain Learning
Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos +2
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant…
Unsupervised Domain Adaptation for Video Transformers in Action Recognition
Victor G. Turrisi da Costa, Giacomo Zara, Paolo Rota +4
Over the last few years, Unsupervised Domain Adaptation (UDA) techniques have acquired remarkable importance and popularity in computer vision. However, when compared to the extens…
Deep Learning-based Type Identification of Volumetric MRI Sequences
Jean Pablo Vieira de Mello, Thiago M. Paixão, Rodrigo Berriel +4
The analysis of Magnetic Resonance Imaging (MRI) sequences enables clinical professionals to monitor the progression of a brain tumor. As the interest for automatizing brain volume…
Copycat CNN: Are Random Non-Labeled Data Enough to Steal Knowledge from Black-box Models?
Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Claudine Badue +2
Convolutional neural networks have been successful lately enabling companies to develop neural-based products, which demand an expensive process, involving data acquisition and ann…
Deep traffic light detection by overlaying synthetic context on arbitrary natural images
Jean Pablo Vieira de Mello, Lucas Tabelini, Rodrigo F. Berriel +5
Deep neural networks come as an effective solution to many problems associated with autonomous driving. By providing real image samples with traffic context to the network, the mod…
Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
Lucas Tabelini, Rodrigo Berriel, Thiago M. Paixão +3
Modern lane detection methods have achieved remarkable performances in complex real-world scenarios, but many have issues maintaining real-time efficiency, which is important for a…
What is the Best Grid-Map for Self-Driving Cars Localization? An Evaluation under Diverse Types of Illumination, Traffic, and Environment
Filipe Mutz, Thiago Oliveira-Santos, Avelino Forechi +4
The localization of self-driving cars is needed for several tasks such as keeping maps updated, tracking objects, and planning. Localization algorithms often take advantage of maps…
Deep Traffic Sign Detection and Recognition Without Target Domain Real Images
Lucas Tabelini, Rodrigo Berriel, Thiago M. Paixão +4
Deep learning has been successfully applied to several problems related to autonomous driving, often relying on large databases of real target-domain images for proper training. Th…
Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents
Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres +4
The reconstruction of shredded documents consists of coherently arranging fragments of paper (shreds) to recover the original document(s). A great challenge in computational recons…
Fast(er) Reconstruction of Shredded Text Documents via Self-Supervised Deep Asymmetric Metric Learning
Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres +4
The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly…
PolyLaneNet: Lane Estimation via Deep Polynomial Regression
Lucas Tabelini, Rodrigo Berriel, Thiago M. Paixão +3
One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has y…
Bio-Inspired Foveated Technique for Augmented-Range Vehicle Detection Using Deep Neural Networks
Pedro Azevedo, Sabrina S. Panceri, Rânik Guidolini +4
We propose a bio-inspired foveated technique to detect cars in a long range camera view using a deep convolutional neural network (DCNN) for the IARA self-driving car. The DCNN rec…
Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images
Lucas Tabelini Torres, Thiago M. Paixão, Rodrigo F. Berriel +4
Deep learning has been successfully applied to several problems related to autonomous driving. Often, these solutions rely on large networks that require databases of real image sa…
Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night
Vinicius F. Arruda, Thiago M. Paixão, Rodrigo F. Berriel +4
Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy…
Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars
Lucas C. Possatti, Rânik Guidolini, Vinicius B. Cardoso +5
Autonomous terrestrial vehicles must be capable of perceiving traffic lights and recognizing their current states to share the streets with human drivers. Most of the time, human d…
Budget-Aware Adapters for Multi-Domain Learning
Rodrigo Berriel, Stéphane Lathuilière, Moin Nabi +4
Multi-Domain Learning (MDL) refers to the problem of learning a set of models derived from a common deep architecture, each one specialized to perform a task in a certain domain (e…
Self-Driving Cars: A Survey
Claudine Badue, Rânik Guidolini, Raphael Vivacqua Carneiro +10
We survey research on self-driving cars published in the literature focusing on autonomous cars developed since the DARPA challenges, which are equipped with an autonomy system tha…
Memory-like Map Decay for Autonomous Vehicles based on Grid Maps
Thomas Teixeira, Filipe Mutz, Karin Satie Komati +5
In this work, we present a novel strategy for correcting imperfections in occupancy grid maps called map decay. The objective of map decay is to correct invalid occupancy probabili…
Ego-Lane Analysis System (ELAS): Dataset and Algorithms
Rodrigo F. Berriel, Edilson de Aguiar, Alberto F. de Souza +1
Decreasing costs of vision sensors and advances in embedded hardware boosted lane related research detection, estimation, and tracking in the past two decades. The interest in this…
Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data
Jacson Rodrigues Correia-Silva, Rodrigo F. Berriel, Claudine Badue +2
In the past few years, Convolutional Neural Networks (CNNs) have been achieving state-of-the-art performance on a variety of problems. Many companies employ resources and money to…
Automatic Large-Scale Data Acquisition via Crowdsourcing for Crosswalk Classification: A Deep Learning Approach
Rodrigo F. Berriel, Franco Schmidt Rossi, Alberto F. de Souza +1
Correctly identifying crosswalks is an essential task for the driving activity and mobility autonomy. Many crosswalk classification, detection and localization systems have been pr…
Visual Global Localization with a Hybrid WNN-CNN Approach
Avelino Forechi, Thiago Oliveira-Santos, Claudine Badue +1
Currently, self-driving cars rely greatly on the Global Positioning System (GPS) infrastructure, albeit there is an increasing demand for alternative methods for GPS-denied environ…