Author

Sathiyamohan Nishankar

h-index 2 View on Semantic Scholar

We have 2 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Does Explainability Transfer? A Controlled Benchmark of Attribution Methods on Vision Transformers and CNNs

A controlled benchmark that evaluates attribution quality across five dimensions: faithfulness, localization, robustness, complexity, and computational cost shows that attribution performance is strongly architecture-dependent and that rankings established on CNNs do not reliably transfer to transformer-based models.

Sathiyamohan Nishankar, Nethmi Pathirana, Pubudu Sanjeewani et al. · 0 citations

#artificial intelligence Preprint Sep 2026

HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives

HiLRP alone preserves conservation across windowed, spatial-reduction, multi-axis, and linear-attention models, where naive extensions can produce zero or inflated relevance, and localizes attribution failures in class activation mapping.

Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera et al. · 0 citations