161 citations · 483 across the 28 of their papers we have counts for
39 papers
Smart Split-Federated Learning over Noisy Channels for Embryo Image Segmentation
Zahra Hafezi Kafshgari, Ivan V. Bajic, Parvaneh Saeedi
Split-Federated (SplitFed) learning is an extension of federated learning that places minimal requirements on the clients computing infrastructure, since only a small portion of th…
Privacy-Preserving Autoencoder for Collaborative Object Detection
Bardia Azizian, Ivan V. Bajic
Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural network (DNN) model runs on the edge, and the rest is executed on the cloud. In such appl…
VVC+M: Plug and Play Scalable Image Coding for Humans and Machines
Alon Harell, Yalda Foroutan, Ivan V. Bajic
Compression for machines is an emerging field, where inputs are encoded while optimizing the performance of downstream automated analysis. In scalable coding for humans and machine…
Rate-Distortion Theory in Coding for Machines and its Application
Alon Harell, Yalda Foroutan, Nilesh Ahuja +6
Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compre…
Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks
Hanieh Naderi, Chinthaka Dinesh, Ivan V. Bajic +1
Adversarial attacks pose serious challenges for deep neural network (DNN)-based analysis of various input signals. In the case of three-dimensional point clouds, methods have been…
Rate-Distortion in Image Coding for Machines
Alon Harell, Anderson De Andrade, Ivan V. Bajic
In recent years, there has been a sharp increase in transmission of images to remote servers specifically for the purpose of computer vision. In many applications, such as surveill…
Towards Automated Key-Point Detection in Images with Partial Pool View
T. J. Woinoski, I. V. Bajic
Sports analytics has been an up-and-coming field of research among professional sporting organizations and academic institutions alike. With the insurgence and collection of athlet…
Efficient Signed Graph Sampling via Balancing & Gershgorin Disc Perfect Alignment
Chinthaka Dinesh, Gene Cheung, Saghar Bagheri +1
A basic premise in graph signal processing (GSP) is that a graph encoding pairwise (anti-)correlations of the targeted signal as edge weights is exploited for graph filtering. Howe…
Collaborative Inference for AI-Empowered IoT Devices
Nir Shlezinger, Ivan V. Bajic
Artificial intelligence (AI) technologies, and particularly deep learning systems, are traditionally the domain of large-scale cloud servers, which have access to high computationa…
Adversarial Attacks on Human Vision
Victor A. Mateescu, Ivan V. Bajić
This article presents an introduction to visual attention retargeting, its connection to visual saliency, the challenges associated with it, and ideas for how it can be approached.…
Scalable Image Coding for Humans and Machines
Hyomin Choi, Ivan V. Bajic
At present, and increasingly so in the future, much of the captured visual content will not be seen by humans. Instead, it will be used for automated machine vision analytics and m…
Latent-space scalability for multi-task collaborative intelligence
Hyomin Choi, Ivan V. Bajic
We investigate latent-space scalability for multi-task collaborative intelligence, where one of the tasks is object detection and the other is input reconstruction. In our proposed…
Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
Robert A. Cohen, Hyomin Choi, Ivan V. Bajić
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a lightweight device such as a mobile phone or edge device, and the remaining portion…
Lightweight compression of neural network feature tensors for collaborative intelligence
Robert A. Cohen, Hyomin Choi, Ivan V. Bajić
In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the rem…
Point Cloud Sampling via Graph Balancing and Gershgorin Disc Alignment
Chinthaka Dinesh, Gene Cheung, Ivan Bajic
3D point cloud (PC) -- a collection of discrete geometric samples of a physical object's surface -- is typically large in size, which entails expensive subsequent operations like v…
Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring
Richard Jones, Christoph Klemenjak, Stephen Makonin +1
Non-Intrusive Load Monitoring (NILM) is a field of research focused on segregating constituent electrical loads in a system based only on their aggregated signal. Significant compu…
Pareto-Optimal Bit Allocation for Collaborative Intelligence
Saeed Ranjbar Alvar, Ivan V. Bajić
In recent studies, collaborative intelligence (CI) has emerged as a promising framework for deployment of Artificial Intelligence (AI)-based services on mobile/edge devices. In CI,…
Affine Transformation-Based Deep Frame Prediction
Hyomin Choi, Ivan V. Bajić
We propose a neural network model to estimate the current frame from two reference frames, using affine transformation and adaptive spatially-varying filters. The estimated affine…
PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
Alon Harell, Richard Jones, Stephen Makonin +1
Non-intrusive load monitoring (NILM) allows users and energy providers to gain insight into home appliance electricity consumption using only the building's smart meter. Most curre…
Soft Video Multicasting Using Adaptive Compressed Sensing
Hadi Hadizadeh, Ivan V. bajic
Recently, soft video multicasting has gained a lot of attention, especially in broadcast and mobile scenarios where the bit rate supported by the channel may differ across receiver…
Back-and-Forth prediction for deep tensor compression
Hyomin Choi, Robert A. Cohen, Ivan V. Bajic
Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor…
Towards Automated Swimming Analytics Using Deep Neural Networks
Timothy Woinoski, Alon Harell, Ivan V. Bajic
Methods for creating a system to automate the collection of swimming analytics on a pool-wide scale are considered in this paper. There has not been much work on swimmer tracking o…
3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals
Chinthaka Dinesh, Gene Cheung, Ivan V. Bajic
Point cloud is a collection of 3D coordinates that are discrete geometric samples of an object's 2D surfaces. Using a low-cost 3D scanner to acquire data means that point clouds ar…
Datasets for Face and Object Detection in Fisheye Images
Jianglin Fu, Ivan V. Bajic, Rodney G. Vaughan
We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images col…