Deep Learning – Spring 2020

 

Class Hours

Tue:  5:30 pm — 7:00 pm,  Thur: 7:15 pm — 8:45 pm
Location LT:1

Office Hours and Contact Info.

Instructor: Mohsen Ali
Office Hours; to be announced
Email: mohsen.ali@itu.edu.pk
Teaching Assistant 1: Muhammad Momin
Office Hours; TBA
Email: msds18025@itu.edu.pk
Teaching Assistant 2: Hamza Rawal
Office Hours; TBA
Email: mscs18004@itu.edu.pk

Course Basics

Core Course
Credit Hours: 3
Being offered to both MSDS, MSCS and BS students
Practical and hands on approach
5 to 6 programming assignments

Prerequisite

Enthusiasm, Energy and Imagination
Data Structures, Probability & Statistics, Linear Algebra and basic Calculus
Programming skills and desire to read & implement.

 

Course Overview

We are going to take “get your hands dirty” approach, you will be given assignments and projects to implement ideas discussed in the class. Projects and assignments will contain miniature versions of real life existing applications and problems (e.g can you train your computer to generate dialogues in Shakespeare style or convert your image into painting as done by Monet, sentiment analysis  etc.. ).
Course will concentrate in developing both mathematical knowledge and implementation capabilities. We will start from training a single perceptron, move to training a deep neural network, study why training large networks is a problem and what could be its possible solutions. After dipping our toes in deep belief networks and recurrent neural network we will start looking into applications of deep learning in three different areas, text-analysis, speech processing and computer vision. Objective of this approach is to make you comfortable enough that you can understand various research problems and, if interested, can implement deep learning based applications.

Course Objectives

In last few years machine learning has matured from the science fiction to reality. We are living in a world where we have already seen industry bringing to reality self-driving cars, face-recognizers that work on massive scale (facebook), speech translation systems that can translate from one language to many other simultaneously and in real-time, and more interestingly we have machines that can learn to play atari games in a similar fashion like we do.
A lot of these victories have come from the exciting field of Deep Learning; a learning methodology based on the concept that human mind captures details at multiple levels or at multiple abstract levels. One property of deep learning is removing the responsibility of humans to design features, instead Deep Learning is given a task to find the appropriate representation.

Grading Policy

  • 45% Assignments
  • 5% Class participation and Creating Notes
  • 20% Final Project
  • 10% Quizzes
  • 10% Midterm Exam
  • 10% Final Exam

Honor Code

All cases of academic misconduct will be forwarded to the disciplinary committee. All assignments are group based unless explicitly specified by the instructor. In the words of Efros, let’s not embarrass ourselves.

Tentative and Rough Course Outline

 

Weeks Topics Evaluations
1 Introduction to Deep Learning

Difference between Machine Learning and Deep Learning

Basic Machine Learning: Linear & Logistic Regression,
2 Supervised Learning with Neural Networks

Deep Learning, Single and Multi-Layer Neural Networks, Perceptron Rule, Gradient Descent, Backpropagation, Loss Functions

Tutorial 1: Python/Numpy Tutorial/Anaconda

 Assignment 1
3 Hyperparameters tuning, Regularization and Optimization

Parameters vs Hyperparameters, Why regularization reduces overfitting? Data Augmentation, Vanishing/Exploding gradients, Weight Initialization Methods, Optimizers

Tutorial 2: Building a Linear Classifier

 Assignment 2
4 Convolutional Neural Networks

Convolutional Filters, Pooling Layers, Classic CNNs: AlexNet, VGG, GoogleNet, ResNet, DenseNet. Transfer Learning

Tutorial 4: CNN Visualization

 Assignment 3

&

Assignment 4
5 Deep Learning for Vision Problems

Object Localization & Detection, Bounding box predictions, Anchor boxes, Region Proposal Networks, Detection Algorithms: RCNN, Faster RCNN, Yolo, SSD.

Tutorial 5: Caffe & Object Detection

 Assignment 5
6 Sequence Models

Recurrent Neural Networks (RNN), Gate Recurrent Unit (GRU), Long Short Term Memory (LSTM), Bidirectional RNN, Backpropagation through time. Image Caption Generation, Machine Translation, Text Generation & Summarization

Tutorial 6: Image Captioning & Text Generation
7 Auto-Encoders & Generative Models

Variational Auto-Encoders, Stacked Auto-Encoders, Denoising Auto-Encoders, Concept of Generative Adversarial Networks (GANs)
8 Miscellaneous

Capsule Networks, Convolutional LSTM, Attention Networks, Restricted Boltzmann Machine, One Shot Learning, Siamese Networks, Triplet Loss, Graph CNN, Approximate and Energy Efficient Design for Deep CNN (Dr. Rehan Hafiz)

 

Course Notes

 

Date Topics Notes / Reading Material / Comments News
4th Feb 2020 Introduction 45% Assignments

20% Final Project

5% Class participation and Creating Notes

10% Quizzes

10% Midterm Exam

10% Final Exam
Recommended Resources
  • Text Book
    • Deep Learning by Ian Goodfellow Link
  • Recommended Online Books
    • Machine Learning, Oxford – Nando de Freitas Link
    • Convolutional Neural Networks for Visual Recognition, Stanford (cs231n) Link
    • A curated list of courses (Recommended) Link
    • Deep Learning for Natural Language Processing, Stanford Link
  • Video Lectures
    • Essence of Neural Networks – 3Blue1Brown Link
    • Convolutional Neural Networks for Visual Recognition, Stanford (cs231n) – Video Lectures Link
    • Neural Networks and Deep Learning – deeplearning.ai – Link
6th Feb 2020 Supervised Learning

Linear Regression
  • Introduction
  • Learning: Supervised, unsupervised. 
  • Learning: discontinuous, continuous
  • Models: bias and variance
  • Linear Regression
    • Error Function in Linear Regression

Assigned Readings:

Recommended Readings:

Refresh

  • Concepts of local minima, local maxima, convex functions, concave functions, critical points, chain rule, saddle point, 
11th and 13th Feb 2020 Logistic Regression
  • Linear Classification
    • Using the Hard Limit Function
  • Logistic Regression
    • Squashing function
    • Sigmoid 
    • Cross Entropy loss function

Assigned Readings:

Recommended Reading on Logistic Regression

Recommended Reading: Softmax and Cross Entropy

 Assigned Readings (Linear Algebra):

    
18th Feb 2020 Gradient Descent

Recommended Readings:

 Posted Assignment 1: Linear Regression with and without Gradient Descent
20th Feb 2020 Optimization
  • Gradient Descent
  • Contrasting 3 Types of Gradient Descent
    • Batch Gradient Descent
    • Stochastic Gradient Descent
    • Mini-Batch Gradient Descent
  • Gradient Descent Optimization Algorithms
    • Momentum
    • Adagrad
    • Adadelta
    • RMSprop
    • Adam
    • AdaMax
  • Visualization of Algorithms
  • Which optimizer to use?

Recommended Readings:
25th Feb 2020 Neural Network
  • Feed-forward Neural Networks
    • Perceptron
      • OR-Function
      • AND-Function 
      • XOR-Function
    • Multiple Perceptron
    • Multiple Layer Neural Network
      • Nonlinear classification (circle)
      • Role of activation functions 
        • hard-limit, sigmoid, tanh, ReLu, leaky ReLu, MaxOut, ELU
    • Input, output and hidden layers
    • Why do we need non-linear functions?
  • How to determine Weights?
  • Computational Graphs
  • Chain Rule
  • Back-propagation Algorithm

Recommended Readings:

Perceptron Rule

Assigned Readings:

Optional:

How to do backpropagation in a brain by Hinton

 Posted Assignment 2: Implementation of Neural Network
27th Feb 2020 Textures and Filters
  • Texture to Convolution Neural Network
    • Texture/ pattern
    • Why is texture important?
    • How to represent texture?
    • Filer Banks/ Masks
      • Stride
      • padding/replicating/mirroring
      • Box Filter, Sobel Filter, Edge Filter
      • Convolution/ Correlation 
10th March CNN continued
  • Texture 
  • Filter Banks
    • Filters to detect edges
    • Filters to detect bars
    • Filters to detect blobs
  • Zero Padding
  • Stride
  • Gaussian Filter
  • Building blocks of CNN
    • Convolutional Layer
    • Pooling Layer
    • Activation Function
      • ReLU
  • Stacking building blocks to build a Deep CNN

NOTES

Assigned Readings

Recommended Readings
12th March 2020 CNN continued
  • CNN for Image Classification
  • Representation power of CNN
  • What is CNN Learning?
  • Different Network Types
    • AlexNet
    • VGG
    • Inception
    • ResNet
    • DenseNet
  • Receptive Field 
  • Effective Receptive Field

Assigned Reading

Recommended Readings

 Posted Assignment 3: Implementation of Convolutional Neural Networks (Forward Propagation only)
19th March CNN 

Backpropagation
  • Backpropagation for Convolutional layer
  • Backpropagation for Pooling layer
  • Converting a FC layer to the Convolutional Layer

Reference 

Video Lecture:

 Posted Assignment 4: Implementation of Convolutional Neural Networks with Backpropagation
Start of Online Lectures after 3 Week break due to Covid-19 outbreak
7th April 2020 NN training
  • Babysitting the learning process
    • Preprocess the data
      • PCA
      • Whitening 
    • Choose the architecture
    • Weight Initialization
      • Xavier
    • Double check the loss is reasonable
    • Hyperparameter Optimization
      • Cross-validation Strategy
9th and 14th April 2020 Batch Normalization and Regularization
  • Regularization
    • Bias/Variance, overfitting, underfitting
    • L1  /L1 regularization
  • Drop Out 
    • Concept of stochastic regularization
    • Forward / backward
  • Batch Normalization

Assigned Readings

Video Lectures

  • Deep Learning – Lecture 4 – Nando de Freitas – Link
16th April 2020 Receptive Field
  • What is a Receptive Field?
    • Relationship with filter size, depth
    • How does a receptive field affect accuracy?
  • Dilated convolution
  • Mixed receptive field
  • 1×1 Convolution 
    • Feature Fusion,
    • Dimensionality reduction or bottleneck layer.  

Assigned Readings
21st April 2020 Popular CNN architectures
  • Transfer Learning 
    • Layers and hierarchical feature learning
    • Freezing and Fine-tuning 
  • Le-Net, AlexNet, VGG, Inception Net, ResNet
  • Link with receptive field
  • Skip layers 
    • Forward propagation
    • Backward propagation
 Posted Assignment 5 – Part 1: Detecting Coronavirus Infections through Chest X-Ray images
23rd April 2020 Popular CNN architectures (continued)
  • Effect of Feature Concatenation
  • CNN for Image Classification
  • Representation power of CNN
  • What is CNN Learning?
  • Different Network Types
    • AlexNet
    • VGG
    • Inception
    • ResNet
    • DenseNet

Assigned Reading

Recommended Readings
24th April 2020 (Tutorial) PyTorch Tutorial Session
  • Data preprocessing, augmentation and loading in PyTorch.
  • Creating custom datasets and data loaders.
  • Creating a neural network:
    • Adding Conv and Linear layers
    • Adding activation, Dropout, Batch Norm layers
    • Defining forward pass (flattening etc.)
    • Defining loss function and optimizer
    • Training loop:
      • Computing loss and gradients
      • Optimizer step
      • Zeroing out gradients
  • Transfer learning:
    • Loading pretrained models (VGG16, ResNet18)
    • Accessing different layers of model
    • Removing and adding personal layers.
    • Freezing and unfreezing layers.
  • Tutorial Recording
30th April 2020 Semantic Segmentation
  • CNN for Semantic Segmentation
    • Deconvolution 
    • Upscaling-convolution
    • Fully Convolutional Network
  • CNN for Instance Segmentation
    • Mask-RCNN

Interesting Reading

 Posted Assignment 5 – Part 2: Focal Loss for Handling Class Imbalance in Detecting Coronavirus Infections
through Chest X-Ray images
5th May 2020 Object Detection
  • Classical view of Object Detection
    • Deformable Parts Based Model
  • CNN for Object Detection
    • R-CNN
    • Fast RCNN
    • Faster RCNN
    • Yolo
    • SSD
12th May 2020 Computer Vision Problems (Continued)
  • Instance Segmentation
  • Panoptic Segmentation
14th May 2020 Sequence Modelling
  • Sequence Modelling
    • Many to one e.g Sentiment Classification
    • Many to many e.g. Translation
  • Recurrent Neural Networks
    • Output dependent on current input and previous hidden state
    • Backpropagation through time
      • Vanishing/Exploding gradients
      • Gated cells allow previous hidden states to bypass current cell
19th May 2020 RNNs (continued)
  • Long Short Term Memory networks
    • Gates to control information flow
  • Multi-layer LSTM
  • Bidirectional LSTM
  • Convolutional LSTM
  • GRU
  • Difference between LSTM and GRU?

Assigned Readings
21st May 2020 Autoencoders
  • Autoencoders
  • Denoising Autoencoders
  • Autoencoders for generating data
  • Relationship between PCA and Autoencoders
  • Stacked Autoencoders
  • Autoencoders for CNN
    • Transpose Convolutions / Deconvolution 

Hugo Larochelle’s lectures are treat – Slides

Reading
2nd June 2020 Autoencoders (continued)
  • Relationship between PCA and Autoencoders
  • Stacked Autoencoders
  • Autoencoders for CNN
    • Transpose Convolutions / Deconvolution 
4th June 2020 GANs
  • Generative Adversarial Networks
    • Two player game (Generator vs Discriminator)
  • ProGAN
  • CycleGAN
  • StyleGAN
  • BigGAN
9th June 2020 Paper Presentations
  • Papers Presented
    • A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets
    • Recurrent convolutional neural networks for text classification
    • GPT2: Language Models are Unsupervised Multitask Learners
    • Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
    • Deep Retinex Decomposition for Low-Light Enhancement
  • Topics Covered:
    • Recurrent Convolutional NN
    • Word2Vec
    • Bidirectional RNN
    • Transformation Architecture
    • Evaluation criteria for caption generation
    • BLEU,  Meteor
    • Micro F1 vs Macro F1
11th June 2020 Presentations (continued)
  • Papers Presented
    • Unsupervised Monocular Depth Estimation with Left-Right Consistency
    • Deep fundamental matrix estimation
    • Improved road connectivity by joint learning of orientation and segmentation
    • Combining satellite imagery and machine learning to predict poverty
    • Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net
    • Cascading YOLO: automated malaria parasite detection for Plasmodium vivax in thin blood smears
    • Deep learning approach to detect malaria from microscopic images
  • Topics Covered
    • Depth estimation using Deep Learning
    • Fundamental Matrix estimation using Deep Learning
    • Satellite imagery processing
    • World-View imagery
    • Hyperspectral imagery
    • Road detection and segmentation
    • Poverty estimation
    • Malaria detection
15th June 2020 Presentations (continued)
  • Papers Presented
    • Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images
    • Drug–Target Affinity Prediction Using Graph Neural Network and Contact Maps
    • Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study
    • Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer
    • Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images
    • Unsupervised domain adaptation for facial expression recognition using generative adversarial networks
    • Deep Domain Adaptation for Facial Expression Analysis
    • U-GAT-IT: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation
  • Topics Covered
    • Graph Neural Networks
    • Drug Affinity Prediction
    • CT scan processing
    • Domain Adaptation
16th June 2020 Presentations (continued)
  • Papers Presented
    • AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
    • Urdu Optical Character Recognition for Twitter Screenshots
    • Stacked capsule autoencoders
    • Fots: Fast oriented text spotting with a unified network
    • Wide Contextual Residual Network with Active Learning for Remote Sensing Image Classification
    • A novel modeling approach for all-dielectric metasurfaces using deep neural networks
    • Generative adversarial imitation learning
 Posted Assignment 6 (Optional): Preparing Slides for Advanced Topics in Deep Learning
End of Lectures

Text Book

  • Text Book: Deep Learning by Ian Goodfellow Link

Recommended Readings

There is not assigned textbook, however following are recommended for reading.

Assignments

  • Assignment 1: Linear Regression with and without Gradient Descent:

  • Assignment 2: Implementation of Neural Network

  • Assignment 3: Implementation of Convolutional Neural Networks

  • Assignment 4: Implementation of CNNs with Backpropagation

  • Assignment 5 – Part 1: Detecting Coronavirus Infections through Chest X-Ray Images

  • Assignment 5 – Part 2: Focal Loss for Handling Class Imbalance in Detecting Coronavirus Infections through Chest X-Ray images

  • Assignment 6: Preparing Slides for Advanced Topics in Deep Learning

 

Projects

 

Project Related Paper Presentations

Group ID Group Members Project Title Paper Details
G1A
  1. Abdur Rehman Ali (MSDS19002)
  2. Muhammad Mehmood Ahmed (MSDS19082)
  3. Muhammad Naeem Maqsood (MSDS19009)
  4. Muhammad Ismaeel (MSDS19029)
 Handwritten Urdu Keyword Recognition using Capsule Networks Kosiorek, Adam, Sara Sabour, Yee Whye Teh, and Geoffrey E. Hinton. “Stacked capsule autoencoders.” In Advances in Neural Information Processing Systems, pp. 15486-15496. 2019.
G1B
  1. Umair Bin Ahmad (MSDS19036)
  2. Abdullah Riaz (MSDS19054)
  3. Muhammad Abubakar (MSDS19086)
  4. Muhammad Mukarram (MSDS19090)
  5. Muhammad Mubashar (MSDS19095)
 Malaria Detection and classification in microscopic images Feng Yang, Nicolas Quizon, Hang Yu, Kamolrat Silamut, Richard J. Maude, Stefan Jaeger, Sameer Antani, “Cascading YOLO: automated malaria parasite detection for Plasmodium vivax in thin blood smears,” Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided
G2B
  1. Ali Haider (MSEE19006)
  2. Ammar Rafique (PhDEE19002)
 Malaria Detection and classification in microscopic images Vijayalakshmi, A. “Deep learning approach to detect malaria from microscopic images.” Multimedia Tools and Applications (2019): 1-21.
G3B
  1. Abdul Rehman (MSDS18009)
  2. Rana Khurram (MSDS18027)
  3. Rana Sarmad (MSDS18047)
 Malaria Detection and classification in microscopic images Rajaraman, Sivaramakrishnan, Stefan Jaeger, and Sameer K. Antani. “Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images.” PeerJ 7 (2019): e6977.
G1D
  1. Muhammad Waheed (PhDEE19004)
  2. Aqsa Tariq (MSDS19075)
  3. Zoya Naseer Hashmi (MSDS19005)
  4. Fatima Farooq Bhatti (MSDS19081)
 Drug Discovery Jiang, Mingjian, Zhen Li, Shugang Zhang, Shuang Wang, Xiaofeng Wang, Qing Yuan, and Zhiqiang Wei. “Drug–Target Affinity Prediction Using Graph Neural Network and Contact Maps,” June 1, 2020. https://doi.org/10.1039/D0RA02297G.
G3E
  1. Uzair Riaz (MSDS18016)
  2. Amir Salman (MSDS18052)
  3. Amir Sharif (MSDS18022)
 Object Detection in the dark/night Wei, Chen, et al. “Deep retinex decomposition for low-light enhancement.” arXiv preprint arXiv:1808.04560 (2018).
G2G
  1. Asif Ejaz (MSDS19010)
  2. Muhammad Sohaib Khalid (MSDS19096)
  3. Amna Shahbaz (MSDS19060)
  4. Jawad Tariq (MSDS19038)
  5. Muhammad Taimur Adil (MSDS19040)
 Domain Adaptation for Emotion Detection from Face Expressions (Western to Pakistani Dramas & Talk Shows) Wang, Xiaoqing, Xiangjun Wang, and Yubo Ni. “Unsupervised domain adaptation for facial expression recognition using generative adversarial networks.” Computational intelligence and neuroscience 2018 (2018).
G3G
  1. Muhammad Suleman Khan (MSDS19011)
  2. Khaqan Ashraf (MSDS19019)
  3. Muhammad Ahmad (MSDS19023)
  4. Muhammad Khubaib Raza (MSDS19064)
 Domain Adaptation for Emotion Detection from Face Expressions (Western to Pakistani Dramas & Talk Shows) Kalischek, Nikolai, Patrick Thiam, Peter Bellmann, and Friedhelm Schwenker. “Deep Domain Adaptation for Facial Expression Analysis.” In 2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), pp. 317-323. IEEE, 2019.
G1H
  1. Fizza Tauqeer (MSDS19034)
  2. Muhammad-ur-Rehman (MSDS19058)
  3. Soban Mahmood (MSCS16012)
 COVID-19 Tweets Analysis M. Jabreel and Antonio Moreno. “A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets.” In the Journal of Multidisciplinary Digital Publishing Institute (MDPI). March ’19, 1-16.
G2H
  1. Obaidullah Ahmad (MSCS19001)
  2. Muhammad Shehryar Khan (MSCS19002)
  3. Abdul Basit (MSCS19003)
  4. Usama Irfan (MSCS19008)
  5. Hadi Mustafa (MSCS19004)
 COVID-19 Tweets Analysis Lai, Siwei, Liheng Xu, Kang Liu, and Jun Zhao. “Recurrent convolutional neural networks for text classification.” In Twenty-ninth AAAI conference on artificial intelligence. 2015.
G3H
  1. Abdul Hameed (MSDS19003)
  2. Adeel Waheed (MSDS19030)
  3. Hamid Ali (MSDS19025)
  4. Muhammad Usman Rasheed (MSDS18038)
  5. Allah Nawaz Qadir (MSDS18069)
 COVID-19 Tweets Analysis Radford, Alec, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. “Language models are unsupervised multitask learners.” OpenAI Blog 1, no. 8 (2019): 9.
G1J
  1. Muhammad Talha Saeed (MSDS19052)
  2. Atika (MSDS19079)
 Urdu Optical Character Recognition for Twitter screenshots Jain, Mohit, Minesh Mathew, and C. V. Jawahar. “Unconstrained ocr for urdu using deep cnn-rnn hybrid networks.” In 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), pp. 747-752. IEEE, 2017.
G1K
  1. Ahad Nadeem (MSDS19044)
  2. Muaaz Zakria (MSDS19053)
  3. Irtaza Haider (MSDS18021)
  4. Osama Nasir (MSDS19012)
  5. Muhammad Huzaifa Bashir (MSDS19026)
 Urdu Caption Generation Liu, Xihui, Hongsheng Li, Jing Shao, Dapeng Chen, and Xiaogang Wang. “Show, tell and discriminate: Image captioning by self-retrieval with partially labeled data.” In Proceedings of the European Conference on Computer Vision (ECCV), pp. 338-354. 2018.
G2K
  1. Faryal Qazi (MSDS17031)
 Urdu Caption Generation Li, Yikang, Wanli Ouyang, Bolei Zhou, Kun Wang, and Xiaogang Wang. “Scene graph generation from objects, phrases and region captions.” In Proceedings of the IEEE International Conference on Computer Vision, pp. 1261-1270. 2017.
G3K
  1. Hafiz Muhammad Abdullah Zia (MSDS19087)
  2. Armughan Ahmad (MSDS19042)
  3. Inaam Ilahi (MSCS18037)
  4. Aitzaz Ehsan (MSCS18045)
  5. Rauf Tabassum (MSCS18030)
 Urdu Caption Generation Xu, Kelvin, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. “Show, attend and tell: Neural image caption generation with visual attention.” In International conference on machine learning, pp. 2048-2057. 2015.
G1L
  1. Muhammad Idrees (MSCS18022)
  2. Abu Bakar Sohail (MSCS18013)
  3. Syed Hashim Shahab (MSCS18011)
 Urdu Text Detection Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., & Yan, J. (2018). Fots: Fast oriented text spotting with a unified network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5676-5685).
G1N
  1. Aoun Ahmed (BSCS17008)
  2. Ammar bin Asim (BSCS17005)
  3. Wassam Safdar (BSCS17028)
  4. Muhammad Junaid Ahmad (BSCS17012)
  5. Fareed ud din Munawwar (BSCS17001)
 Deep Fundamental Matrix Estimation or Depth Estimation Godard, Clement, Oisin Mac Aodha, and Gabriel J. Brostow. “Unsupervised Monocular Depth Estimation with Left-Right Consistency.” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
G3N
  1. Iqra Jawaid (MSEE19024)
 Deep Fundamental Matrix Estimation or Depth Estimation Ranftl, René, and Vladlen Koltun. “Deep fundamental matrix estimation.” In Proceedings of the European Conference on Computer Vision (ECCV), pp. 284-299. 2018.
G1O
  1. Muhammad Burhan (MSDS19032)
  2. Nauman Akram (MSDS19041)
  3. Dareer Ahmed (MSDS19061)
  4. Muhammad Muneeb (MSDS19091)
  5. Muhammad Sohaib (MSDS18071)
 Urban analysis through Satellite Imagery Batra, Anil, Suriya Singh, Guan Pang, Saikat Basu, C. V. Jawahar, and Manohar Paluri. “Improved road connectivity by joint learning of orientation and segmentation.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10385-10393. 2019.
G2O
  1. Hadia Irshad (MSDS19016)
  2. Kainat Altaf (MSDS19014)
  3. Momin Ali (MSDS19070)
  4. Hafiz Muhammad Nadeem (MSDS19007)
 Urban analysis through Satellite Imagery Jean, Neal, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, and Stefano Ermon. “Combining satellite imagery and machine learning to predict poverty.” Science 353, no. 6301 (2016): 790-794.
G3O
  1. Usman Tariq (MSDS18048)
  2. Ahmed Saleem (MSDS18026)
  3. Muhammad Haseeb Ali (MSDS18037)
  4. Farrukh Butt (MSDS18058)
 Urban analysis through Satellite Imagery Pan, Zhuokun, Jiashu Xu, Yubin Guo, Yueming Hu, and Guangxing Wang. “Deep Learning Segmentation and Classification for Urban Village Using a Worldview Satellite Image Based on U-Net.” Remote Sensing 12, no. 10 (2020): 1574.
G2F
  1. Basir Mahmood (MSDS19043)
  2. Usama Muneer (MSDS19077)
  3. Muhammad Shafeeq (MSDS19078)
 Pakistani Avatar Generation using GANs Kim, Junho, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee. “U-GAT-IT: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation.” arXiv preprint arXiv:1907.10830 (2019).
G3F
  1. Muhammad Hamad Akram (MSEE19018)
  2. Nasir Aziz (MSEE19004)
 Pakistani Avatar Generation using GANs Tang, Hao, Hong Liu, Dan Xu, Philip HS Torr, and Nicu Sebe. “Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks.” arXiv preprint arXiv:1911.11897 (2019).
G1S
  1. Hafiz Muhammad Sheharyar (MSDS19065)
  2. Haseeb Ali (MSDS19033)
  3. Hamza Ahmed (MSDS19069)
 Brain Hemorrhage Detection Chilamkurthy, Sasank, Rohit Ghosh, Swetha Tanamala, Mustafa Biviji, Norbert G. Campeau, Vasantha Kumar Venugopal, Vidur Mahajan, Pooja Rao, and Prashant Warier. “Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study.” The Lancet 392, no. 10162 (2018): 2388-2396.
G1T
  1. Badar Shaban (BSCS16069)
  2. Taha Muzammil (BSCS16063)
  3. Awais Mushtaq (BSCS16033)
  4. Soban Asif (BSCS16022)
  5. Khaleel Ahmad (BSCS16015)
 Food Analysis on Hyperspectral Imagery using Deep Learning Liu, Shengjie, Haowen Luo, Ying Tu, Zhi He, and Jun Li. “Wide contextual residual network with active learning for remote sensing image classification.” In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 7145-7148. IEEE, 2018.
G1U
  1. Sumbel Ijaz (PhDEE19003)
 A novel modelling approach for all-dielectric metasurfaces using deep neural networks An, Sensong, Clayton Fowler, Bowen Zheng, Mikhail Y. Shalaginov, Hong Tang, Hang Li, Li Zhou et al. “A novel modeling approach for all-dielectric metasurfaces using deep neural networks.” arXiv preprint arXiv:1906.03387 (2019).
G1V
  1. Bilal Rana (MSDS19066)
  2. Muhammad Irfan Umar (MSDS19027)
  3. Mudasser Afzal (MSDS19067)
  4. Muhammad Sufian (MSDS17037)
 Prostate Cancer Grade Assessment Nagpal, Kunal, Davis Foote, Yun Liu, Po-Hsuan Cameron Chen, Ellery Wulczyn, Fraser Tan, Niels Olson et al. “Development and validation of a deep learning algorithm for improving Gleason scoring of prostate cancer.” NPJ digital medicine 2, no. 1 (2019): 1-10.
G1W
  1. Usman Anwar (MSDS19001)
 Imitation Learning On Atari Games Using GAIL Ho, Jonathan, and Stefano Ermon. “Generative adversarial imitation learning.” In Advances in neural information processing systems, pp. 4565-4573. 2016.
G1X
  1. Syed Sadiq Ali Naqvi (MSDS19004)
  2. Muhammad Zaid (MSDS19006)
 Attention based Multiple Instance learning for medical image analysis Lu, Ming Y., Drew FK Williamson, Tiffany Y. Chen, Richard J. Chen, Matteo Barbieri, and Faisal Mahmood. “Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images.” arXiv preprint arXiv:2004.09666 (2020).

 

 

Toolkits

Caffe

●      Toolkit Page

●      Online Caffe Help

●      Caffe Pretrained Models

 TensorFlow

●      Toolkit Page

●      Online Discussion and Help Forum

●      Tensoflow Pretrained Models
Torch

●      Toolkit Page

●      Online Help Forum

●      Pretrained Models

 Keras

●      Toolkit Page

●      Online Help Forum

●      Pretrained Models

 

Some Interesting Links