Search Results for author:
Found 8 papers, 5 papers with code
T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
While some techniques for generating explanations have been proposed, primarily for Convolutional Neural Networks, adapting such techniques to the new paradigm of Vision Transformers is non-trivial.
Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion
Face detectors are becoming a crucial component of many applications, including surveillance, that often have to run on edge devices with limited processing power and memory.
Masked Feature Modelling: Feature Masking for the Unsupervised Pre-training of a Graph Attention Network Block for Bottom-up Video Event Recognition
In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block.
Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism
In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed.
TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks
TAME can easily be applied to any convolutional neural network (CNN) by streamlining the optimization of the attention mechanism's training method and the selection of target model's feature maps.
Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanism
In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed.
ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network
In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task of event recognition and explanation in video, is proposed.
Accelerated kernel discriminant analysis
In this paper, using a novel matrix factorization and simultaneous reduction to diagonal form approach (or in short simultaneous reduction approach), Accelerated Kernel Discriminant Analysis (AKDA) and Accelerated Kernel Subclass Discriminant Analysis (AKSDA) are proposed.
