CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916959035064320 |
|---|---|
| author | Chakraborty, Ritabrata Dasgupta, Avijit Chaurasia, Sandeep |
| author_facet | Chakraborty, Ritabrata Dasgupta, Avijit Chaurasia, Sandeep |
| contents | Visual explanations are often plausible but not structurally faithful. We introduce CAMBench-QR, a structure-aware benchmark that leverages the canonical geometry of QR codes (finder patterns, timing lines, module grid) to test whether CAM methods place saliency on requisite substructures while avoiding background. CAMBench-QR synthesizes QR/non-QR data with exact masks and controlled distortions, and reports structure-aware metrics (Finder/Timing Mass Ratios, Background Leakage, coverage AUCs, Distance-to-Structure) alongside causal occlusion, insertion/deletion faithfulness, robustness, and latency. We benchmark representative, efficient CAMs (LayerCAM, EigenGrad-CAM, XGrad-CAM) under two practical regimes of zero-shot and last-block fine-tuning. The benchmark, metrics, and training recipes provide a simple, reproducible yardstick for structure-aware evaluation of visual explanations. Hence we propose that CAMBENCH-QR can be used as a litmus test of whether visual explanations are truly structure-aware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16745 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding Chakraborty, Ritabrata Dasgupta, Avijit Chaurasia, Sandeep Computer Vision and Pattern Recognition Artificial Intelligence Visual explanations are often plausible but not structurally faithful. We introduce CAMBench-QR, a structure-aware benchmark that leverages the canonical geometry of QR codes (finder patterns, timing lines, module grid) to test whether CAM methods place saliency on requisite substructures while avoiding background. CAMBench-QR synthesizes QR/non-QR data with exact masks and controlled distortions, and reports structure-aware metrics (Finder/Timing Mass Ratios, Background Leakage, coverage AUCs, Distance-to-Structure) alongside causal occlusion, insertion/deletion faithfulness, robustness, and latency. We benchmark representative, efficient CAMs (LayerCAM, EigenGrad-CAM, XGrad-CAM) under two practical regimes of zero-shot and last-block fine-tuning. The benchmark, metrics, and training recipes provide a simple, reproducible yardstick for structure-aware evaluation of visual explanations. Hence we propose that CAMBENCH-QR can be used as a litmus test of whether visual explanations are truly structure-aware. |
| title | CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.16745 |