7 papers
The Quest for Universal Master Key Filters in DS-CNNs
Zahra Babaiee, Peyman M. Kiassari, Daniela Rus +1
A recent study has proposed the "Master Key Filters Hypothesis" for convolutional neural network filters. This paper extends this hypothesis by radically constraining its scope to…
Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
Tony Lindeberg, Zahra Babaiee, Peyman M. Kiasari
This paper presents the results of analysing and modelling a set of 8 ``master key filters'', which have been extracted by applying a clustering approach to the receptive fields le…
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to rec…
Are Programming Paradigms Paradigms? A Critical Examination of Floyd's Appropriation of Kuhn's Philosophy
Peyman M. Kiasari
This paper examines the philosophical relationship between Thomas Kuhn's concept of scientific paradigms and the programming paradigm concept in computing that was introduced by Fl…
The Master Key Filters Hypothesis: Deep Filters Are General
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clus…
Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
Recent advances in depthwise-separable convolutional neural networks (DS-CNNs) have led to novel architectures, that surpass the performance of classical CNNs, by a considerable sc…