Reza A. Profile

5.0

(11 reviews)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$20 USD / hour

aachen,

germany

$20 USD / hour

It's currently 5:53 PM here

Joined December 16, 2019

1 Recommendation

Reza A.

@rezadeeplearning

5.0

(11 reviews)

4.4

33%

$20 USD / hour

aachen,

germany

$20 USD / hour

100%

Jobs Completed

99%

On Budget

100%

On Time

18%

Repeat Hire Rate

Deep learning and Computer vision researcher

I am PhD student in computer vision and machine learning filed. My main research ambition is to propose state of the art methods for real world application. I have published several research paper in the are of computer vision, machine learning and deep learning. I have strong software and implementation experience in computer vision and machine learning area. Please check my Github to see some of publicly available implementation: [login to view URL] You can check my research publication in my google scholar bellow: [login to view URL] I am expert with the following deep learning libraries: Keras Tensorflow Pytorch I follow state of the art papers (CVPR, ICCV, ECCV, MICCAI) in the deep learning area, specially for semantic Image segmentation, Medical image analysis, few-shot learning, action recognition, self-driving car, continual learning, active learning and ... Please contact me .

See all Deep Learning Specialists in Germany

Contact Reza A. about your job

Portfolio

Implementation code for my Semi-supervised approach for few-shot semantic medical image segmentation. This method is the first attempt to apply the episodic training paradigm for few-shot medical image segmentation. This method also enriches the feature representation in an unsupervised manner. More specifically, this method boosts the encoder representation with including surrogate task. Experimental results on two well-know Skin Lesion Segmentation data sets have been demonstrated that the proposed method produces promising results.

Semi-supervised Few-Shot Learning for Medical Image Segmenta

I have developed an deep LSTM model to Predict stock price using time series information. For this project I have used several years information to model the fluctuation and learn the hidden pattern, then I have modeled the output as a next week price information. Based on the validation set the prediction performance looks promising. I would love to extended this model for further improvement.

Stock price prediciton

6850249

Auto-encoder decoder model for semantic segmentation

Implementation of the deeplab version 3+ for semantic segmentation. I also have developed famous networks such as U-net, Attention U-net, Deeplab, Retina Net and etc for semantic segmentation. All codes implemented in both pytoch and tensorflow. Amazing results on public datasets.

Semantic segmetnation

Multi-object detection

In this project I have implemented and trained the Yolo3 model on Coco dataset for real-time car detection and tracking. For tracking part I have developed the extended version of Kalman filter. The code works in real-time with amazing performance. The Yolo3 model is attached.

Implementation of the Yolo 3 Model for real time detection

Semi-supervised Few-Shot Learning for Medical Image Segmenta

Stock price prediciton

6850249

Auto-encoder decoder model for semantic segmentation

Semantic segmetnation

Multi-object detection

Implementation of the Yolo 3 Model for real time detection

Reviews

Changes saved

Showing 1 - 5 out of 11 reviews

Filter reviews by:

5.0

£80.00 GBP

Project for Reza A. -- 20/10/21 00:22:29

Reza is a great person, very cooperative and talented . He does his job in a very professional way, try all possible best solutions and always on time.

+1 more

Naji A.

@naji59431

•

4 years ago

5.0

$800.00 USD

Project for Reza A.

Reza is a very skilled professional and does everything to understand and solve the problem and to deliver a perfect job with a fair budget. Exceeded my expectations.

+1 more

Dg S.

@sthln

•

4 years ago

5.0

$22.00 USD

Digital Image Processing

He is highly skilled, talented and provide detailed attention to the problem to come up with the solution in a timely manner.

Python

Machine Learning (ML)

Tensorflow

Computer Vision

Deep Learning

Shariq A.

@shareqahmed

•

4 years ago

5.0

$100.00 USD

Project for Reza A. -- 20/10/05 22:19:11

Very professional and expert in the field. Delivered the project on time. Has exceeded my expectation. I highly recommend him.

+1 more

Naji A.

@naji59431

•

4 years ago

5.0

₹10,000.00 INR

Project for Reza A.

The best person to work with, his professionalism, communication and quality of work is excellent.

+1 more

Jatin G.

@RigaBlack

•

4 years ago

Experience

Tose Dade Pardaz Mehr

Sep 2017 - Sep 2018 (1 year)

Worked as a software developer for the machine learning and computer vision part. Projects involved from different range including medical, computer vision, NLP and speech processing.

Education

M.Sc.

Sharif University of Technology,

Iran, Islamic Republic of

2015 - 2017

(2 years)

Qualifications

SRTTU

2013

Awarded the best researcher certificate due to the publication record in top conference and journals.

Publications

New method for optimization of license plate recognition system with use of edge detection

IEEE International Conference on Computer and Knowledge Engineering 2013

An automated approach for License Plate recognition system has been proposed. In this paper, a fast and real time method utilized using edge and structural information to take the problem of license plate recognition in tilt and poor quality condition.

Real-Time Human Face Detection in Noisy Images Based on Skin Color Fusion Model and Eye Detection

Springer Intelligent Computing, Communication and Devices 2015

Automatic human face detection in noisy images. In this paper, we propose a method that includes a de-noising per-processing step and a new face detection approach based on skin color fusion model and eye region detection.

Dynamic 3D Hand Gesture Recognition by Learning Weighted Depth Motion Maps

IEEE Transactions on Circuits and Systems for Video Technology 2018

Hand gesture recognition (HGR) from sequences of depth maps with proposing novel ideas of multilevel temporal sampling(MTS) method and the weighted depth motion map (WDMM) approach.

Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation

ECCV, European Conference on Computer Vision 2020

In this paper, we propose Attention Deeplabv3+, an extended version of Deeplabv3+ for skin lesion segmentation by employing the idea of attention mechanism in two stages. We first capture the relationship between the channels of a set of feature maps by assigning a weight for each channel then by including the the second level attention strategy to integrate different layers of the atrous convolution.

Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions

ICCV 2019

In this paper, we propose an extension of U-Net, Bi-directional ConvLSTM U-Net with Densely connected convolutions (BCDU-Net), for medical image segmentation, in which we take full advantages of U-Net, bi-directional ConvLSTM (BConvLSTM) and the mechanism of dense convolutions. The proposed model is evaluated on three datasets of: retinal blood vessel segmentation, skin lesion segmentation, and lung nodule segmentation, achieving state-of-the-art performance.