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

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

A controlled evaluation of 13 attribution methods across CNN and Vision Transformer architectures using five quality and cost dimensions.

Released

2026-08-03

Evaluates

General AI, Robustness, Safety & Trustworthiness, cs.CV

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.02396

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

• Paper https://arxiv.org/abs/2608.02396
• Code https://github.com/Nishan-Charlie/VIT_XAI_Bench

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

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

Related General AI, Robustness, Safety & Trustworthiness, cs.CV benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 360CityArena
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench