Search Results for author: Domenec Puig

Found 24 papers, 10 papers with code

Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks

2 code implementations Mendel 2022 Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan, Domenec Puig

In Deep Convolutional Neural Networks (DCNNs), the parameter count in pointwise convolutions quickly grows due to the multiplication of the filters and input channels from the preceding layer.

Image Classification

GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network

1 code implementation13 Dec 2021 Armin Masoumian, Hatem A. Rashwan, Saddam Abdulwahab, Julian Cristiano, Domenec Puig

In particular, our method provided comparable and promising results with a high prediction accuracy of 89% on the publicly KITTI and Make3D datasets along with a reduction of 40% in the number of trainable parameters compared to the state of the art solutions.

3D Reconstruction Depth Prediction +1

T-YOLO: Tiny Vehicle Detection Based on YOLO and Multi-Scale Convolutional Neural Networks

no code implementations IEEE Access 2021 Daniel Padilla Carrasco, Hatem RashwanHatem Rashwan, Miguel Ángel García, Domenec Puig

In fact, as shown in the experiments, the results show a small reduction from 7. 28 million parameters of the YOLO-v5-S profile to 7. 26 million parameters in our model.

 Ranked #1 on Parking Space Occupancy on PKLot (using extra training data)

object-detection Object Detection +1

Absolute distance prediction based on deep learning object detection and monocular depth estimation models

1 code implementation2 Nov 2021 Armin Masoumian, David G. F. Marei, Saddam Abdulwahab, Julian Cristiano, Domenec Puig, Hatem A. Rashwan

Determining the distance between the objects in a scene and the camera sensor from 2D images is feasible by estimating depth images using stereo cameras or 3D cameras.

Monocular Depth Estimation object-detection +1

Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet

1 code implementation 23rd International Conference of the Catalan Association for Artificial Intelligence 2021 Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan, Domenec Puig

Our proposal is to improve the pointwise (1x1) convolutions, whose number of parameters rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer.

Image Classification

AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation

no code implementations11 Oct 2021 Syeda Furruka Banu, Md. Mostafa Kamal Sarker, Mohamed Abdel-Nasser, Domenec Puig, Hatem A. Raswan

Accurate lung nodule detection and segmentation in computed tomography (CT) images is the most important part of diagnosing lung cancer in the early stage.

Computed Tomography (CT) Lung Nodule Detection +1

Adversarial Learning with Multiscale Features and Kernel Factorization for Retinal Blood Vessel Segmentation

no code implementations5 Jul 2019 Farhan Akram, Vivek Kumar Singh, Hatem A. Rashwan, Mohamed Abdel-Nasser, Md. Mostafa Kamal Sarker, Nidhi Pandey, Domenec Puig

In this paper, we propose an efficient blood vessel segmentation method for the eye fundus images using adversarial learning with multiscale features and kernel factorization.

SLSNet: Skin lesion segmentation using a lightweight generative adversarial network

1 code implementation1 Jul 2019 Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Farhan Akram, Vivek Kumar Singh, Syeda Furruka Banu, Forhad U H Chowdhury, Kabir Ahmed Choudhury, Sylvie Chambon, Petia Radeva, Domenec Puig, Mohamed Abdel-Nasser

Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model.

Image Segmentation Lesion Segmentation +2

An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning

no code implementations1 Jul 2019 Vivek Kumar Singh, Hatem A. Rashwan, Mohamed Abdel-Nasser, Md. Mostafa Kamal Sarker, Farhan Akram, Nidhi Pandey, Santiago Romani, Domenec Puig

We propose to add an atrous convolution layer to the conditional generative adversarial network (cGAN) segmentation model to learn tumor features at different resolutions of BUS images.

General Classification SSIM +1

Identification and Visualization of the Underlying Independent Causes of the Diagnostic of Diabetic Retinopathy made by a Deep Learning Classifier

no code implementations23 Sep 2018 Jordi de la Torre, Aida Valls, Domenec Puig, Pere Romero-Aroca

In this paper we go forward into the generation of explanations by identifying the independent causes that use a deep learning model for classifying an image into a certain class.

General Classification Medical Diagnosis

Retinal Optic Disc Segmentation using Conditional Generative Adversarial Network

no code implementations11 Jun 2018 Vivek Kumar Singh, Hatem Rashwan, Farhan Akram, Nidhi Pandey, Md. Mostaf Kamal Sarker, Adel Saleh, Saddam Abdulwahab, Najlaa Maaroof, Santiago Romani, Domenec Puig

Then, the discriminator learns as a loss function to train this mapping by comparing the ground-truth and the predicted output with observing the input image as a condition. Experiments were performed on two publicly available dataset; DRISHTI GS1 and RIM-ONE.

Image Segmentation Optic Disc Segmentation +1

A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading

no code implementations21 Dec 2017 Jordi de la Torre, Aida Valls, Domenec Puig

Deep neural network models have been proven to be very successful in image classification tasks, also for medical diagnosis, but their main concern is its lack of interpretability.

General Classification Image Classification +1

Analyzing Stability of Convolutional Neural Networks in the Frequency Domain

no code implementations10 Nov 2015 Elnaz J. Heravi, Hamed H. Aghdam, Domenec Puig

Understanding the internal process of ConvNets is commonly done using visualization techniques.

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