Neural architeuct generation using Diffusion modeling
In this project we will exemine changing NN architecture to be more robust / less computationaly heavy, using classifier free diffusion models
Posts by Collection
projects
Learn with Noisy Labels in segmentation
Investigate the biasses of self annotation and how to combat noisy labels in segmentation tasks
Real-time Instance Segmentation
Formulate the segmentation task as regression only
Mixing augmentation for semi supervised learning
Generate new insights about how and what to mix
Increase the latency of LLM
By adverserial attack
Semi Supervised Segmentation for 3D cardiac data
Levreging previus work
publications
Bimodal Distributed Binarized Neural Networks
Published in Mathematics 10 (21), 2022
In this work, we propose bimodal-distributed binarization method, for better create binary neural networks
Download here
AMED: Automatic Mixed-Precision Quantization for Edge Devices
Published in Mathematics 12 (12), 2023
This work look at quantization of neural network as a markov decision process
Download here
Robot Instance Segmentation with Few Annotations for Grasping
Published in Preprint, 2024
We improve perception for robotic grasping with temporal and identification consistency
Download here
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
Published in Transactions on Machine Learning Research (06/2024), 2024
We refine pseudo-labeling process for semantic segmentation task using contextual information
Download here
Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters
Published in Preprint, 2024
We propose a benchmark for spatial label nosise for instanse segmentation, both with man main and machine made noise
Download here
talks
Talk about efficient models
Published:
I gave a talk to the workers of Linvo about efficient modeling, compration, quantization and NAS, challenges and current state-of-the-art on edge devices.
teaching
Computer vision
Workshop, Technion, EE faculty, 2021
Teaching 046746 - From SIFT and templete matching to Deep learning for tracking
Deep Learning
combined Undergrad and Grad course, Technion, CS + Raichman, CS, 2022
Head TA for cs236781. I am the head TA, means all tutorials and home assignments under my responsibilities. We’ve created a course with three segments