4 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…
Benchmarking CNN and Transformer-Based Object Detectors for UAV Solar Panel Inspection
Ashen Rodrigo, Isuru Munasinghe, Pubudu Sanjeewani +1
Timely and accurate detection of defects and contaminants in solar panels is critical for maintaining the efficiency and reliability of photovoltaic (PV) systems. While recent stud…