Photos from the Event
Gathering & Poster Session
13:30-14:00
Welcome
14:00-14:10
Prof. David Malah, Head of SIPL
Improving Training Efficiency in Deep Learning
14:10-14:35
Prof. Daniel Soudry
Abstract:
I will present several empirical and theoretical results related to improving training efficiency in deep networks, based on the following works:
- Elad Hoffer, Itay Hubara, and Daniel Soudry, “Fix your classifier: the marginal value of training the last weight layer.” ICLR 2018.
- Elad Hoffer, Ron Banner, Itay Golan, and Daniel Soudry, “Norm matters: efficient and accurate normalization schemes in deep networks.” arXiv 2018.
- Ron Banner, Itay Hubara, Elad Hoffer, and Daniel Soudry, “Scalable methods for 8-bit training of neural networks.” arXiv 2018.
Wilk Family Awards and Outstanding Supervisor Awards Ceremony
14:35-14:45
Unsynchronized Acoustic Indoor Positioning
14:45-15:05
2nd prize winner in the Kasher undergraduate project contest in the Faculty of Electrical Engineering
Guy Feferman, Michal Blatt
Supervisor: Alon Eilam
In cooperation with: 
ICASSP 2018 Demo
Break & Poster Session
15:05-15:35
Review of Teaching Activity in SIPL
15:35-15:50
Nimrod Peleg
Detection and Localization of Cumulonimbus Clouds in Satellite Images
15:50-16:10
Wilk family award winner
Etai Wagner, Ron Dorfman
Supervisor: Almog Lahav
In cooperation with: 
Submitted to ICSEE 2018
Local-to-Global Point Cloud Registration using a Viewpoint Dictionary
16:10-16:35
David Avidar, M.Sc. student
Advisors: Prof. David Malah, Dr. Meir Bar-Zohar
Partly funded by the OMEK consortium
Presented at ICCV 2017
Abstract:
Local-to global point cloud registration is a challenging task due to the substantial differences between these two types of data, and the different techniques used to acquire them. Global clouds cover large-scale environments and are usually acquired aerially (e.g., using Airborne Laser Scanning – ALS), and local clouds are often acquired from ground level at a much smaller range (e.g., using Terrestrial Laser Scanning – TLS). As a result of these differences, existing point cloud registration approaches, such as keypoint-based registration, tend to fail.
We propose a novel registration method based on converting the global cloud into a viewpoint-based dictionary. We associate each viewpoint with a panoramic range-image, capturing the geometry of the visible environment. Then, plausible local-to-global transformations can be found via a dictionary search. We show efficient dictionary search can be done using phase-correlation between panoramic range-images.
We demonstrate that the proposed viewpoint-dictionary-based registration method achieves better performance than state-of-the-art, keypoint-based methods (e.g., FPFH, RoPS), even without any GPS measurements. For the evaluation, we used a challenging dataset of 108 TLS local clouds and an ALS large-scale global cloud, in a 1km2 urban environment.
The Perception-Distortion Tradeoff
16:35-17:00
Yochai Blau, Ph.D. student
Advisor: Prof. Tomer Michaeli
Presented at CVPR 2018
Abstract:
Image restoration algorithms are typically evaluated by some distortion measure (e.g. PSNR, SSIM, IFC, VIF) or by human opinion scores that quantify perceived perceptual quality. In this work, we prove mathematically that distortion and perceptual quality are at odds with each other. Specifically, we study the optimal probability for correctly discriminating the outputs of an image restoration algorithm from real images. We show that as the mean distortion decreases, this probability must increase (indicating worse perceptual quality). As opposed to the common belief, this result holds true for any distortion measure, and is not only a problem of the PSNR or SSIM criteria. However, as we show experimentally, for some measures it is less severe (e.g. distance between VGG features). We also show that generative-adversarial-nets (GANs) provide a principled way to approach the perception-distortion bound. This constitutes theoretical support to their observed success in low-level vision tasks. Based on our analysis, we propose a new methodology for evaluating image restoration methods, and use it to perform an extensive comparison between recent super-resolution algorithms. Our study reveals which methods are currently closest to the theoretical perception-distortion bound.
Posters
| Project Title | Students | Supervisor | Comments / Collaboration |
|---|---|---|---|
| Acoustic positioning with unsynchronized sound sources | Guy Feferman Michal Blatt | Alon Eilam | Guy Shofen Sonarax |
| Influence of Motion on Video Quality Perception | Ido Lev and Ilan Meltzer | Yair Moshe | Harmonic |
| General Road Detection From A Single Image | Dudi Lubton | Yair Moshe | |
| Interference Cancellation for Underwater Acoustic Signals | Eitan Ovrutski Sapir Madi | Dr. Roee Diamant | |
| Peripheral Vascular Disease - Walking Pattern Recognition | Sztyglic Ori Septon Shay | Ofer Danino | Prof. Aharon Hoffman (Rambam hospital) |
| Android Application for Audio QR | Ron Steinberg Zvi Herscovici | Alon Eilam | Sonarax |
| Detection and Localization of Cumulonimbus Clouds in Satellite Images | Ron Dorfman and Etai Wagner | Almog Lahav | Wilk Award 2018, RAFAEL |
| Audio Retrieval by Voice Imitation | Samah Khawaled Mohamad Khatib | Dr. Hadas Benisty | Wilk Award 2018 |
| Monitoring Vital Signs of Children in Intensive Care | Ifat Abramovich and Tomer Ben Yehuda | Or Yair | Dr. Danny Eytan (Rambam hospital) |
| Estimating Brain Activation Patterns from EEG Data | Ronen Rahamim and Gilad Hecht | Or Yair | Dr. Danny Eytan (Rambam hospital) |
| Differential Microphone Arrays (DMA) Demo System | Ronen Sheffi | Kobi Bucris and Dr. Evyatar Hemo | RAFAEL |
| Semi-Supervised Classification of Acoustic Signals | Inbar Rachel Frenkel | Ron Amit | RAFAEL |
| Real-Estate market estimation Using Machine Learning algorithms | Roei Shemesh and Nitzan Krasney | Jonatan Chernyak | |
| Detect and Classify Species of Fish | Shalom Lagziel | Idan Kligvasser | |
| Teaching Deep Networks to Improvise Jazz | Yamin Ben Shimon Shunit Haviv | Nadav Bhonker | |
| Revealing ADHD from functional MRI | Yossi Levi Itzik Merkado | Supervised by Andrey Zhitnikov | Prof. Tzipi Horowitz-Kraus, Technion |
| Reading Difficulty Detection using Eye Movements | Jonathan Shani Yoni Osin | Or Yair | Prof. Tzipi Horowitz-Kraus |
| News Stories Classification Using Online Deep Learning | Inna Batenkov Yoni Lederman | Yaron Ezra | RAFAEL |
| Classification of dolphin's whistles using Deep Learning | Matan Tur-paz Shahaf Aricha | Yaron Doweck and Dr. Alon Amar | RAFAEL |
| Recognition of PVD based on Walking Pattern Acquired from Smartphone | Ori Cohen Samyon Shahnovitch | Supervised by Ofer Danino and Erez Fridman | Prof. Aaaron Hoffman |
| Speech Enhancement Using Deep Learning | Ariel Zelman Tzvika Sweetkin | Yohai Blau and Dr. David Dov | Elbit Systems |
| Fast Video Encoding using Deep Learning | Omri Carmi and Harel Hasky | Yair Moshe | Harmonic In progress |
| Alarm Sound Detection Using Deep Learning | Yoni Lederman and Naor Fadida | Yair Moshe | In progress |
| Towards Blood Pressure Estimation Using a Smartphone Camera | Ido Lev and Inbal Ronai | Yair Moshe | In progress |
| Identification Of Content In Images Of Promotional Brochures | Gil Gelbert Ilan Meltzer | Ori Bryt | QuantaCom In progress |
| Clustering of Sounds in Humpback Whale Singing | Gal Harush Inbal Kom-Betzer | Dr. Alon Amar and Yaron Doweck | RAFAEL In progress |
| Artifact Reduction From Brain Activity Signals | Barak Hoffer Einav Aharon | Dr. David Dov | Alpha-Omega In progress |
| Examination of TMS Effect Using EEG Signal | Matan Allouche Reggev Livney | Or Yair | BrainsWay In progress |
| Video Classification Using Deep Learning | Ifat Abramovich Tomer Ben Yehuda | Dr. Rami Cohen | In progress |
| Efficient Deep Learning for Pedestrian Traffic Light Recognition | Roni Ash Dolev Ofri | Yair Moshe | In progress |
| Heart Disease Detection from Human Voice | Ben Dgani Eli Szulc | Supervised by Kfir Shem-Tov | CardioKol In progress |
| Gesture Recognition With a Smart Bracelet | Andre Kassis Majd Abu Tayeh | Ariel Schwartz | In progress |
| Multi-Microphone Speaker Localization Demo System | Avi Semo Alon Saguy | Kobi Bucris and Dr. Evyatar Hemo | In progress |
| Anomaly Detection on Chest X-Rays with Deep Learning | Yair Yarden Ofir Kedem | Yair Moshe | In progress |
| Deep Learning for Classroom Augmented Reality Application | Tom Kratter Yonatan Sackstein | Yair Moshe | In progress |
| Color Calibration For Smart Product Labels | Gil Gelbert | Ori Bryt | FreshPoint In progress |
| Detection and Analysis of Dolphin Sounds | Guy Shkury Yoel Bud | Dr. Roee Diamant | In progress |
| Signal Processing Algorithms Development and Implementation with Android DSP Lab | Matanel Yaacov Shay Avig | Alon Eilam | In progress |
| Android App for Detecting Alarm Sounds | Rachel Gringols Michal Kuperman Koren | Alon Eilam and Yair Moshe | In progress |
| Synthesis of Mammography Images Using Deep Learning | Lotem Manassen Inbar Kazes | Yochai Blau and Idan Kligvasser | IBM In progress |
| Acoustic Beamformer with a Constant Beamwidth for Planar Array | Roni Ash Arkadi Gurevich | Dr. Baruch Berdugo | Israel Police Dept. In progress |
| Estimating Brain Activation Patterns from EEG Data | Gal Maman | Or Yair and Prof. Ronen Talmon | Dr. Danny Eitan In progress |
| Cardiac Arrest Prediction Based on Geometric Modeling of Pediatric CCU Monitor Data | Gal Shachaf | Tal Shnitzer and Prof. Ronen Talmon | Dr. Danny Eytan In progress |
| Learning to Deform for Efficient Image Compression | Elad Hirsch Nadav Eliyahu | Tamar Rott and Idan Kligvasser | In progress |
| Wind Noise Reduction from Speech Signals | Adir Kobovich Tomer Lerner | Tal Shnitzer | Waves In progress |
| Relative Camera Pose Estimation Using Smartphone Cameras and Sensors | Omer Movshovitz Guy Dascalu | Ori Bryt and Adam Wolff | RAFAEL In progress |
| Stitching Corrections For Aerial Images Using Deep Learning | Tomer Rosenbaum and Dror Kabely | Ori Bryt | RAFAEL In progress |
| Residual Echo Suppression Using Deep Learning | Aya Ganem Omer London | Andrey Zhitnikov | In progress |
| Semi-supervised Learning for Acoustic Source Localization and Tracking | Avner Okun Barak Gerstein | Ori Kats | In progress |
| Android App for Detecting Alarm Sounds | Rachel Gringols Michal Kuperman Koren | Alon Eilam and Yair Moshe | In progress |
| Obtaining Physical Laws Empirically with Manifold Learning | Kobi Shiran Gal Kinberg | Or Yair | Mr. Ofer Danino In progress |
| Interactive Demo Systemfor 3D Depth Data Processing | Lital Filber and Ori Lador, | Yair Moshe | In progress |
| From Deep Features To Image Restoration | Ori Sztyglic | Tamar Rott Shaham and Idan Kligvasser | In progress |
| Image Compression Using Deep Learning Techniques | Idan Berkovich Omer Gal | Supervised by Ori Bryt, Nadav Bhonker, Dr. Ron Rubinstein | In progress |
| Real-time Audio Processing for Android | Ivan Zorin Alex Dashevski | Nimrod Peleg and Pavel Lifshits | In progress |