165 citations · 536 across the 24 of their papers we have counts for
29 papers
Retraining-Free Depth Pruning of Vision Transformers: A Cross Domain Study of Layer Redundancy
Alessandro Viespoli, Loris Nanni
Transformer architectures have achieved strong results in natural language processing and computer vision, but their deployment is limited by high computational, memory and storage…
Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
Marco Stefani, Edoardo Parpaiola, Matteo Bino +5
High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation across Convolutional Neural Net…
A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning
Taha Shieenavaz, Shabnam Zareshahraki, Loris Nanni
Replay-free parallelized Q-learning removes the large experience replay buffers and target networks used by conventional deep Q-learning, but the role of network architecture in th…
Feature transforms for image data augmentation
Loris Nanni, Michelangelo Paci, Sheryl Brahnam +1
A problem with Convolutional Neural Networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many method…
Deep ensembles in bioimage segmentation
Loris Nanni, Daniela Cuza, Alessandra Lumini +2
Semantic segmentation consists in classifying each pixel of an image by assigning it to a specific label chosen from a set of all the available ones. During the last few years, a l…
Gated recurrent units and temporal convolutional network for multilabel classification
Loris Nanni, Alessandra Lumini, Alessandro Manfe +3
Multilabel learning tackles the problem of associating a sample with multiple class labels. This work proposes a new ensemble method for managing multilabel classification: the cor…