Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion

Read full text Summarise with VIRAT
Authors: Abu Noman Sakib, O. F. M. Riaz Rahman Aranya, Kevin Desai, Zijie Zhang
Cited by: 0
References: 40

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Attribution maps for semantic segmentation are almost always judged by visual plausibility. Yet looking convincing does not guarantee that the highlighted pixels actually drive the model's prediction, nor that attribution credit stays within the target region. These questions require a dedicated evaluation protocol. We introduce a reproducible benchmark that tests intervention-based faithfulness, off-target leakage, perturbation robustness, and runtime on Pascal VOC and SBD across three pretrained backbones. To further demonstrate the benchmark, we propose Dual-Evidence Attribution (DEA), a lightweight correction that fuses gradient evidence with region-level intervention signals through agreement-weighted fusion. DEA increases emphasis where both sources agree and retains causal support when gradient responses are unstable. Across all completed runs, DEA consistently improves deletion-based faithfulness over gradient-only baselines and preserves strong robustness, at the cost of additional compute from intervention passes. The benchmark exposes a faithfulness-stability tradeoff among attribution families that is entirely hidden under visual evaluation, providing a foundation for principled method selection in segmentation explainability. Code is available at https://github.com/anmspro/DEA.

Fields of Study & Subjects

Explainable Artificial Intelligence (XAI) Advanced Neural Network Applications Software Testing and Debugging Techniques

Publication details

Journal / source
arXiv (Cornell University)
Publication date
23 March 2026
Language
EN
Document type
Preprint