Research map / Vision-language and multimodal / CLIP and zero-shot
Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework
Ziqi Sheng, Junyan Wu, Wei Lu, Jiantao Zhou
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 |
|---|---|---|---|
| add coarse classification loss (ablation) | ViLaCo · CASIA | IF1: 0.410 -> 0.491 | Improved |
| add fine localization loss (ablation) | ViLaCo · CASIA | IF1: 0.365 -> 0.491 | Improved |
| add contrastive patch consistency loss (ablation) | ViLaCo · IMD20 | IF1: 0.320 -> 0.365 | Improved |
| add contrastive patch consistency loss (ablation) | ViLaCo · CASIA | PF1: 0.860 -> 0.880 | Improved |
| use 8x8 patch block size (ablation) | ViLaCo · detection and localization | accuracy-efficiency trade-off | Improved |
| use CLIP vision-language guidance versus prior weakly supervised methods | ViLaCo · four-dataset average | combined F1: 0.441 -> 0.593 (vs MRL-Net) | Improved |
| ViLaCo versus MRL-Net on image-level detection on Columbia | ViLaCo · Columbia | image-level F1: 0.975 -> 0.917 | Hurt |
Closest papers by meaning
- SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints (AAAI 2025 · similarity 0.89)
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.88)
- M²RL-Net: Multi-View and Multi-Level Relation Learning Network for Weakly-Supervised Image Forgery Detection (AAAI 2025 · similarity 0.88)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.87)
- Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis (NeurIPS 2025 · similarity 0.87)
- OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL (ICML 2026 · similarity 0.87)
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.
