activity
20182022
most citedEdge-PRUNE: Flexible Distributed Deep Learning Inference

1 citations · 1 across the 4 of their papers we have counts for

collaborators

10 papers

cs.LG2022

SADT: Combining Sharpness-Aware Minimization with Self-Distillation for Improved Model Generalization

Masud An-Nur Islam Fahim, Jani Boutellier

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to…

cs.SD2022

Multiple Offsets Multilateration: a new paradigm for sensor network calibration with unsynchronized reference nodes

Luca Ferranti, Kalle Åström, Magnus Oskarsson +2

Positioning using wave signal measurements is used in several applications, such as GPS systems, structure from sound and Wifi based positioning. Mathematically, such problems requ…

cs.DC20221 cited

Edge-PRUNE: Flexible Distributed Deep Learning Inference

Jani Boutellier, Bo Tan, Jari Nurmi

Collaborative deep learning inference between low-resource endpoint devices and edge servers has received significant research interest in the last few years. Such computation part…

math.NA2021

Homotopy Continuation for Sensor Networks Self-Calibration

Luca Ferranti, Kalle Åström, Magnus Oskarsson +2

Given a sensor network, TDOA self-calibration aims at simultaneously estimating the positions of receivers and transmitters, and transmitters time offsets. This can be formulated a…

cs.CV2021

LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

Abol Basher, Muhammad Sarmad, Jani Boutellier

Recently, several works have addressed modeling of 3D shapes using deep neural networks to learn implicit surface representations. Up to now, the majority of works have concentrate…

cs.CV2020

Can You Trust Your Pose? Confidence Estimation in Visual Localization

Luca Ferranti, Xiaotian Li, Jani Boutellier +1

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has fo…