RobustDeepfakeCVPR26 Models

--- license: mit tags: - deepfake-detection - image-classification - robustness - self-blended-images - ensemble - cvpr - ntire library_name: pytorch pipeline_tag: image-classification --- # RobustDeepfakeCVPR26 — AI4Good greedy6 ensemble Model checkpoints for **Team AI4Good / SoloUNI**'s submission to the **NTIRE 2026 Robust Deepfake Detection Challenge** (CVPR 2026 Workshop). **Method — Self-Supervised Adversarial Training.** Binary classifiers trained on the **500 real images only** using **Self-Blended Images (SBI)** + **PMM degradation**. No real fakes are used — pseudo-fakes are generated on-the-fly from pairs of real images via landmark-guided Poisson/Alpha blending. Six diverse backbones are trained independently and combined by probability averaging with 3× deterministic TTA. - **Code & reproduction:** https://github.com/CristianLazoQuispe/RobustDeepfakeCVPR26 - **Method writeup (arXiv):** https://arxiv.org/abs/2604.24163 - **Challenge report (CVPR 2026):** [Hopf et al., *Robust Deepfake Detection, NTIRE 2026 Challenge: Report*](https://openaccess.thecvf.com/content/CVPR2026W/NTIRE/html/Hopf_Robust_Deepfake_Detection_NTIRE_2026_Challenge_Report_CVPRW_2026_paper.html) - **License:** MIT ## The 6 models Each file is `<model>/best.pt` — a PyTorch checkpoint dict with keys including `model` (state_dict), `epoch`, `best_auc`, and the full training `config`. All trained at 224×224, AdamW, cosine 100 epochs, `seed: 42` (`csl` uses 43), `deterministic: true`, `amp: false`. | Model | Backbone (`timm`) | In ch. | Hard-Test AUC | Val AUC | |:--|:--|:--:|:--:|:--:| | `r3d_fa_csb` | `convnext_base.fb_in22k_ft_in1k` | 3 | **0.7644** | 0.897 | | `lmhm_css` | `convnext_small.fb_in22k_ft_in1k` + LMHM | 4 | 0.7268 | 0.900 | | `r3e_fa_css` | `convnext_small.fb_in22k_ft_in1k` | 3 | 0.7259 | 0.844 | | `r3d_fa_csl_s43` | `convnext_large.fb_in22k_ft_in1k` | 3 | 0.7127 | 0.867 | | `r3d_fa_deit3_s` | `deit3_small_patch16_224` | 3 | 0.7111 | 0.889 | | `lmhm_vits` | `vit_small_patch16_224.augreg_in21k_ft_in1k` + LMHM | 4 | 0.6945 | 0.899 | | **Ensemble (6) + TTA** | — | — | **0.7777** | — | > **CodaBench Public Test AUC: 0.6865** (submission 632762, 6-model ensemble + TTA). > *Hard-Test AUC* is on a local 500-real/500-fake degraded holdout; *Val AUC* is the in-training best. > `LMHM` = landmark-heatmap models take a 4-channel input (RGB + face-landmark heatm...

Source context: 0 downloads · 0 likes · Pipeline image-classification · Library pytorch · Repo CristianLazoQuispe/RobustDeepfakeCVPR26-models