7 citations · 11 across the 15 of their papers we have counts for
16 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…
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…
Scalable Offline Reinforcement Learning for Mean Field Games
Axel Brunnbauer, Julian Lemmel, Zahra Babaiee +2
Reinforcement learning algorithms for mean-field games offer a scalable framework for optimizing policies in large populations of interacting agents. Existing methods often depend…
Segmentation of Prostate Tumour Volumes from PET Images is a Different Ball Game
Shrajan Bhandary, Dejan Kuhn, Zahra Babaiee +5
Accurate segmentation of prostate tumours from PET images presents a formidable challenge in medical image analysis. Despite considerable work and improvement in delineating organs…
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…
Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields
Zahra Babaiee, Peyman M. Kiasari, Daniela Rus +1
In this study, we present evidence suggesting that depthwise convolutional kernels are effectively replicating the structural intricacies of the biological receptive fields observe…
Prediction of Tourism Flow with Sparse Geolocation Data
Julian Lemmel, Zahra Babaiee, Marvin Kleinlehner +5
Modern tourism in the 21st century is facing numerous challenges. Among these the rapidly growing number of tourists visiting space-limited regions like historical cities, museums…
IB-U-Nets: Improving medical image segmentation tasks with 3D Inductive Biased kernels
Shrajan Bhandary, Zahra Babaiee, Dejan Kostyszyn +4
Despite the success of convolutional neural networks for 3D medical-image segmentation, the architectures currently used are still not robust enough to the protocols of different s…
Pruning by Active Attention Manipulation
Zahra Babaiee, Lucas Liebenwein, Ramin Hasani +2
Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-sco…
Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data
Julian Lemmel, Zahra Babaiee, Marvin Kleinlehner +5
Modern tourism in the 21st century is facing numerous challenges. One of these challenges is the rapidly growing number of tourists in space limited regions such as historical city…
Entangled Residual Mappings
Mathias Lechner, Ramin Hasani, Zahra Babaiee +4
Residual mappings have been shown to perform representation learning in the first layers and iterative feature refinement in higher layers. This interplay, combined with their stab…
End-to-End Sensitivity-Based Filter Pruning
Zahra Babaiee, Lucas Liebenwein, Ramin Hasani +2
In this paper, we present a novel sensitivity-based filter pruning algorithm (SbF-Pruner) to learn the importance scores of filters of each layer end-to-end. Our method learns the…
3D-OOCS: Learning Prostate Segmentation with Inductive Bias
Shrajan Bhandary, Zahra Babaiee, Dejan Kostyszyn +4
Despite the great success of convolutional neural networks (CNN) in 3D medical image segmentation tasks, the methods currently in use are still not robust enough to the different p…
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Zahra Babaiee, Ramin Hasani, Mathias Lechner +2
Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks w…