Lovm: Language-only vision model selection

O Zohar, SC Huang, KC Wang… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular
due to their exceptional performance on downstream vision applications, particularly in the …

Tapas: Train-less accuracy predictor for architecture search

R Istrate, F Scheidegger, G Mariani… - Proceedings of the AAAI …, 2019‏ - aaai.org
In recent years an increasing number of researchers and practitioners have been
suggesting algorithms for large-scale neural network architecture search: genetic …

Precision-weighted federated learning

J Reyes, L Di Jorio, C Low-Kam… - arxiv preprint arxiv …, 2021‏ - arxiv.org
Federated Learning using the Federated Averaging algorithm has shown great advantages
for large-scale applications that rely on collaborative learning, especially when the training …

A comparative analysis of deep neural network architectures for sentence classification using genetic algorithm

B Rogers, N Noman, S Chalup, P Moscato - Evolutionary Intelligence, 2024‏ - Springer
Because of the number of different architectures, numerous settings of their hyper-
parameters and disparity among their sizes, it is difficult to equitably compare various deep …

Clustered redundant keypoint elimination method for image mosaicing using a new Gaussian-weighted blending algorithm

Z Hossein-Nejad, M Nasri - The Visual Computer, 2022‏ - Springer
In this paper, a new method for image mosaicing (image stitching) is introduced based on
Scale Invariant Feature transform (SIFT). One of the main drawbacks of SIFT is the …

Multiclass classification by Min–Max ECOC with Hamming distance optimization

G Szűcs - The Visual Computer, 2023‏ - Springer
Two questions often arise in the field of the ensemble in multiclass classification problems,(i)
how to combine base classifiers and (ii) how to design possible binary classifiers. Error …

Predicting the Encoding Error of SIRENs

J Vonderfecht, F Liu - arxiv preprint arxiv:2410.21645, 2024‏ - arxiv.org
Implicit Neural Representations (INRs), which encode signals such as images, videos, and
3D shapes in the weights of neural networks, are becoming increasingly popular. Among …

What can we Learn by Predicting Accuracy?

O Risser-Maroix, B Chamand - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
This paper seeks to answer the following question:" What can we learn by predicting
accuracy?". Indeed, classification is one of the most popular tasks in machine learning, and …

Constrained deep neural network architecture search for IoT devices accounting for hardware calibration

F Scheidegger, L Benini, C Bekas… - Advances in Neural …, 2019‏ - proceedings.neurips.cc
Deep neural networks achieve outstanding results for challenging image classification tasks.
However, the design of network topologies is a complex task, and the research community is …

An intelligent hierarchical residual attention learning‐based conjoined twin neural network for Alzheimer's stage detection and prediction

VG Shankar, DS Sisodia… - Computational …, 2023‏ - Wiley Online Library
Alzheimer's disorder (AD) causes permanent impairment in the brain's memory of the
cellular system, leading to the initiation of dementia. Earlier detection of Alzheimer's disease …