Research map / Architectures and efficiency / Attention and transformers
BioTamperNet: Affinity-Guided State-Space Model Detecting Tampered Biomedical Images
Soumyaroop Nandi, Prem Natarajan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use BioTamperNet instead of best prior method on BioFors EDD | BioFors EDD · BioFors EDD combined | image-level MCC: 0.438 -> 0.701 | Improved |
| Use BioTamperNet instead of best prior method on BioFors IDD | BioFors IDD · BioFors IDD combined | image-level MCC: 0.569 -> 0.701 | Improved |
| Use BioTamperNet on FACS EDD pixel-level | BioFors EDD FACS · BioFors EDD FACS | pixel-level MCC: 0.504 -> 0.448 | Hurt |
| Use BioTamperNet instead of TruFor on CSTD | BioFors CSTD · BioFors CSTD | image-level MCC: 0.173 -> 0.514 | Improved |
| Add a global SSM layer after affinity-guided enrichment (ablation) | BioTamperNet · BioFors | MCC | No clear effect |
| Add affinity and SSM components (vs CNN or ViT-MHA replacement) (ablation) | BioTamperNet · BioFors | MCC | Improved |
| Add domain-adaptive batch normalization for cross-modality fine-tuning (ablation) | BioTamperNet · BioFors cross-modality | source MCC: naive fine-tuning: -17.2% source MCC | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SparseViT — SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer (CVPR 2023) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space Modeling (AAAI 2026 · similarity 0.86)
- ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization (NeurIPS 2025 · similarity 0.82)
- Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis (NeurIPS 2025 · similarity 0.82)
- Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images (NeurIPS 2026 · similarity 0.82)
- Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection (CVPR 2025 · similarity 0.81)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
