Zobrazeno 1 - 10
of 194
pro vyhledávání: '"Bajić, Ivan"'
Autor:
Hadizadeh, Hadi, Bajić, Ivan V.
Autonomous driving sensors generate an enormous amount of data. In this paper, we explore learned multimodal compression for autonomous driving, specifically targeted at 3D object detection. We focus on camera and LiDAR modalities and explore several
Externí odkaz:
http://arxiv.org/abs/2408.08211
Autor:
Ulhaq, Mateen, Bajić, Ivan V.
The entropy bottleneck introduced by Ball\'e et al. is a common component used in many learned compression models. It encodes a transformed latent representation using a static distribution whose parameters are learned during training. However, the a
Externí odkaz:
http://arxiv.org/abs/2406.13059
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. SplitFed aims to minimize the computational burden on indi
Externí odkaz:
http://arxiv.org/abs/2405.19453
In recent years, there has been a significant increase in applications of multimodal signal processing and analysis, largely driven by the increased availability of multimodal datasets and the rapid progress in multimodal learning systems. Well-known
Externí odkaz:
http://arxiv.org/abs/2405.12456
Autor:
de Andrade, Anderson, Bajić, Ivan
We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount of informat
Externí odkaz:
http://arxiv.org/abs/2405.10244
Autor:
Alvar, Saeed Ranjbar, Bajić, Ivan V.
Deep models produce a number of features in each internal layer. 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. The problem is especi
Externí odkaz:
http://arxiv.org/abs/2405.09077
Autor:
Azizian, Bardia, Bajic, Ivan V.
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 applications, the machine vision model does not need the exact visual cont
Externí odkaz:
http://arxiv.org/abs/2402.18864
Autor:
Ulhaq, Mateen, Bajić, Ivan V.
Due to the limited computational capabilities of edge devices, deep learning inference can be quite expensive. One remedy is to compress and transmit point cloud data over the network for server-side processing. Unfortunately, this approach can be se
Externí odkaz:
http://arxiv.org/abs/2402.12532
Autor:
Ulhaq, Mateen, Bajić, Ivan V.
Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited computational capab
Externí odkaz:
http://arxiv.org/abs/2308.05959
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). The goal of SFL is to reduce the computational powe
Externí odkaz:
http://arxiv.org/abs/2307.13851