activity
20162025
most citedDomain-adversarial neural networks to address the appearance variability of histopathology images

1.1k citations · 2.2k across the 32 of their papers we have counts for

collaborators
Showing 2022Show all

15 papers · 1 filter

cs.CL2022★ 131 cited

A survey on text generation using generative adversarial networks

Gustavo Henrique de Rosa, João Paulo Papa

This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text ge…

cs.CV2022★ 2 cited

Video Segmentation Learning Using Cascade Residual Convolutional Neural Network

Daniel F. S. Santos, Rafael G. Pires, Danilo Colombo +1

Video segmentation consists of a frame-by-frame selection process of meaningful areas related to foreground moving objects. Some applications include traffic monitoring, human trac…

cs.CV2022★ 4 cited

DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification

Daniel F. S. Santos, Rafael G. Pires, Leandro A. Passos +1

Research on remote sensing image classification significantly impacts essential human routine tasks such as urban planning and agriculture. Nowadays, the rapid advance in technolog…

cs.AI2022

Improving Pre-Trained Weights Through Meta-Heuristics Fine-Tuning

Gustavo H. de Rosa, Mateus Roder, João Paulo Papa +1

Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classific…

cs.LG2022★ 4 cited

FEMa-FS: Finite Element Machines for Feature Selection

Lucas Biaggi, João P. Papa, Kelton A. P Costa +2

Identifying anomalies has become one of the primary strategies towards security and protection procedures in computer networks. In this context, machine learning-based methods emer…

cs.LG2022★ 11 cited

PL-kNN: A Parameterless Nearest Neighbors Classifier

Danilo Samuel Jodas, Leandro Aparecido Passos, Ahsan Adeel +1

Demands for minimum parameter setup in machine learning models are desirable to avoid time-consuming optimization processes. The -Nearest Neighbors is one of the most effective…