Search Results for author:
Found 40 papers, 11 papers with code
Learned Multimodal Compression for Autonomous Driving
Autonomous driving sensors generate an enormous amount of data.
Learned Compression of Encoding Distributions
To address this issue, we propose a method that dynamically adapts the encoding distribution to match the latent data distribution for a specific input.
Optimizing Split Points for Error-Resilient SplitFed Learning
Recent advancements in decentralized learning, such as Federated Learning (FL), Split Learning (SL), and Split Federated Learning (SplitFed), have expanded the potentials of machine learning.
Mutual Information Analysis in Multimodal Learning Systems
Taking advantage of the recent progress in entropy modeling and estimation, we develop a system called InfoMeter to estimate MI between modalities in a multimodal learning system.
Compressive Feature Selection for Remote Visual Multi-Task Inference
A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model.
Scalable Human-Machine Point Cloud Compression
In this paper, we present a scalable codec for point-cloud data that is specialized for the machine task of classification, while also providing a mechanism for human viewing.
Learned Point Cloud Compression for Classification
Our codec demonstrates the potential of specialized codecs for machine analysis of point clouds, and provides a basis for extension to more complex tasks and datasets in the future.
SplitFed resilience to packet loss: Where to split, that is the question
Decentralized machine learning has broadened its scope recently with the invention of Federated Learning (FL), Split Learning (SL), and their hybrids like Split Federated Learning (SplitFed or SFL).
Metaverse: A Young Gamer's Perspective
When developing technologies for the Metaverse, it is important to understand the needs and requirements of end users.
Learned Scalable Video Coding For Humans and Machines
Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on.
Base Layer Efficiency in Scalable Human-Machine Coding
A basic premise in scalable human-machine coding is that the base layer is intended for automated machine analysis and is therefore more compressible than the same content would be for human viewing.
Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence
Collaborative intelligence (CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud.
Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey
To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification. This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years.
Conditional and Residual Methods in Scalable Coding for Humans and Machines
We present methods for conditional and residual coding in the context of scalable coding for humans and machines.
Quality-Adaptive Split-Federated Learning for Segmenting Medical Images with Inaccurate Annotations
SplitFed Learning, a combination of Federated and Split Learning (FL and SL), is one of the most recent developments in the decentralized machine learning domain.
Multi-Task Learning for Screen Content Image Coding
With the rise of remote work and collaboration, compression of screen content images (SCI) is becoming increasingly important.
LCCM-VC: Learned Conditional Coding Modes for Video Compression
End-to-end learning-based video compression has made steady progress over the last several years.
Privacy-Preserving Feature Coding for Machines
We present a novel method to create a privacy-preserving latent representation of an image that could be used by a downstream machine vision model.
Adversarial Attacks on Human Vision
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.
Joint Image Compression and Denoising via Latent-Space Scalability
In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly.
License Plate Privacy in Collaborative Visual Analysis of Traffic Scenes
Traffic scene analysis is important for emerging technologies such as smart traffic management and autonomous vehicles.
Does Video Compression Impact Tracking Accuracy?
Everyone "knows" that compressing a video will degrade the accuracy of object tracking.
Practical Noise Simulation for RGB Images
This document describes a noise generator that simulates realistic noise found in smartphone cameras.
SFU-HW-Tracks-v1: Object Tracking Dataset on Raw Video Sequences
We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences.
DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels
In edge-cloud collaborative intelligence (CI), an unreliable transmission channel exists in the information path of the AI model performing the inference.
CALTeC: Content-Adaptive Linear Tensor Completion for Collaborative Intelligence
In collaborative intelligence, an artificial intelligence (AI) model is typically split between an edge device and the cloud.
Error Resilient Collaborative Intelligence via Low-Rank Tensor Completion
The communication channel between the edge and cloud is imperfect, which will result in missing data in the deep feature tensor received at the cloud side.
Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
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 of the DNN is processed where more computing resources are available, such as in the cloud.
Lightweight compression of neural network feature tensors for collaborative intelligence
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 remainder of the DNN is processed where more computing resources are available, such as in the cloud.
Swimmer Stroke Rate Estimation From Overhead Race Video
In this work, we propose a swimming analytics system for automatically determining swimmer stroke rates from overhead race video (ORV).
Collaborative Intelligence: Challenges and Opportunities
This paper presents an overview of the emerging area of collaborative intelligence (CI).
Analysis of Latent-Space Motion for Collaborative Intelligence
When the input to a deep neural network (DNN) is a video signal, a sequence of feature tensors is produced at the intermediate layers of the model.
Latent-Space Inpainting for Packet Loss Concealment in Collaborative Object Detection
Edge devices, such as cameras and mobile units, are increasingly capable of performing sophisticated computation in addition to their traditional roles in sensing and communicating signals.
Analysis of Information Flow Through U-Nets
Deep Neural Networks (DNNs) have become ubiquitous in medical image processing and analysis.
Pareto-Optimal Bit Allocation for Collaborative Intelligence
Moreover, we provide analytical characterization of the full Pareto set for 2-stream k-task systems, and bounds on the Pareto set for 3-stream 2-task systems.
Bit Allocation for Multi-Task Collaborative Intelligence
In CI, a deep neural network is split between the mobile device and the cloud.
Shared Mobile-Cloud Inference for Collaborative Intelligence
Partial inference is performed on the mobile in order to reduce the dimensionality of the input data and arrive at a compact feature tensor, which is a latent space representation of the input signal.
Wavenilm: A causal neural network for power disaggregation from the complex power signal
Non-intrusive load monitoring (NILM) helps meet energy conservation goals by estimating individual appliance power usage from a single aggregate measurement.
MV-YOLO: Motion Vector-aided Tracking by Semantic Object Detection
Object tracking is the cornerstone of many visual analytics systems.
