5 papers
M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image Models
Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera
Quantitative evaluation of generative models for radiology remains challenging. Clinically relevant structures are often small and infrequent, feature spaces learned from natural i…
HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera +1
Vision Transformer (ViT) design has become increasingly diverse, with backbones combining convolutional stems, windowed, linear, or multi-axis attention, patch merging, and spatial…
Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs
Sathiyamohan Nishankar, Nethmi Pathirana, Pubudu Sanjeewani +2
Most evidence on the effectiveness of explainable artificial intelligence (XAI) attribution methods has been established on convolutional neural networks (CNNs), with limited inves…
UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification
Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan +1
Vision Transformers (ViTs) have demonstrated strong representation capability in image classification. However, their quadratic self-attention complexity and large parameter counts…
U-FedTomAtt: Ultra-lightweight Federated Learning with Attention for Tomato Disease Recognition
Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan +4
Federated learning has emerged as a privacy-preserving and efficient approach for deploying intelligent agricultural solutions. Accurate edge-based diagnosis across geographically…