26 citations · 41 across the 10 of their papers we have counts for
11 papers
DynaGuide: A Generalizable Dynamic Guidance Framework for Unsupervised Semantic Segmentation
Boujemaa Guermazi, Riadh Ksantini, Naimul Khan
Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where…
DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity
Boujemaa Guermazi, Naimul Khan
Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, th…
A Dynamically Weighted Loss Function for Unsupervised Image Segmentation
Boujemaa Guermazi, Riadh Ksantini, Naimul Khan
Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promis…
A Contrastive Variational Graph Auto-Encoder for Node Clustering
Nairouz Mrabah, Mohamed Bouguessa, Riadh Ksantini
Variational Graph Auto-Encoders (VGAEs) have been widely used to solve the node clustering task. However, the state-of-the-art methods have numerous challenges. First, existing VGA…
Graph Attention Network for Camera Relocalization on Dynamic Scenes
Mohamed Amine Ouali, Mohamed Bouguessa, Riadh Ksantini
We devise a graph attention network-based approach for learning a scene triangle mesh representation in order to estimate an image camera position in a dynamic environment. Previou…
Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering
Nairouz Mrabah, Mohamed Bouguessa, Mohamed Fawzi Touati +1
Most recent graph clustering methods have resorted to Graph Auto-Encoders (GAEs) to perform joint clustering and embedding learning. However, two critical issues have been overlook…
Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters
Ahmed Zgaren, Wassim Bouachir, Riadh Ksantini
During the last years, deep learning trackers achieved stimulating results while bringing interesting ideas to solve the tracking problem. This progress is mainly due to the use of…
Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift
Nairouz Mrabah, Mohamed Bouguessa, Riadh Ksantini
Clustering using deep autoencoders has been thoroughly investigated in recent years. Current approaches rely on simultaneously learning embedded features and clustering the data po…
Deep Clustering with a Dynamic Autoencoder: From Reconstruction towards Centroids Construction
Nairouz Mrabah, Naimul Mefraz Khan, Riadh Ksantini +1
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smo…
A Novel Image-centric Approach Towards Direct Volume Rendering
Naimul Khan, Riadh Ksantini, Ling Guan
Transfer Function (TF) generation is a fundamental problem in Direct Volume Rendering (DVR). A TF maps voxels to color and opacity values to reveal inner structures. Existing TF to…
Incremental One-Class Models for Data Classification
Takoua Kefi, Riadh Ksantini, M. Becha Kaaniche +1
In this paper we outline a PhD research plan. This research contributes to the field of one-class incremental learning and classification in case of non-stationary environments. Th…