Update README: published DOI, final 224-res CV numbers, fix under-review status

README.md

@@ -17,8 +17,9 @@ language:
 
 Trained checkpoints for **GoldFormer** and baseline models from the paper:
 
-> **GoldFormer: A Texture-Aware Vision Transformer-based Algorithm for Detecting Near-Identical Images**  
-> Z. Raisi, *Algorithms* (MDPI), under review.  
+> **GoldFormer: A Texture-Aware Vision Transformer-Based Algorithm for Detecting Near-Identical Images**  
+> Z. Raisi, *Algorithms* (MDPI), 2026, 19(7), 530.  
+> DOI: [10.3390/a19070530](https://doi.org/10.3390/a19070530). Open access (CC BY 4.0).  
 > Code & dataset: [github.com/zobeirraisi/GoldNet](https://github.com/zobeirraisi/GoldNet)
 
 ## Task
@@ -27,37 +28,49 @@ Binary image classification — **authentic vs. counterfeit gold items** — fro
 
 ## Available Checkpoints (`weights/`)
 
-| File | Model | Accuracy (5-fold CV) |
-|---|---|---|
-| `GoldFormer_best.pth` | GoldFormer (CNN + Swin-T + TAAG) | 94.69 ± 0.79% |
-| `Swin_T_best.pth` | Swin Transformer-Tiny | 94.31 ± 0.78% |
-| `ViT_B16_best.pth` | ViT-B/16 | 94.31 ± 0.94% |
-| `ResNet101_best.pth` | ResNet-101 | 92.29 ± 1.01% |
-| `ResNet50_best.pth` | ResNet-50 | — |
-| `ResNet18_best.pth` | ResNet-18 | — |
-| `DenseNet121_best.pth` | DenseNet-121 | — |
-| `EfficientNet_B3_best.pth` | EfficientNet-B3 | — |
-| `EfficientNet_B0_best.pth` | EfficientNet-B0 | — |
-| `MobileNet_V2_best.pth` | MobileNet-V2 | — |
-
-All models trained with 5-fold stratified cross-validation, AdamW, AMP (bfloat16), freeze-then-unfreeze fine-tuning on the GoldNet dataset (2,127 images, 1,044 authentic / 1,083 counterfeit).
+Results below are 5-fold stratified cross-validation at matched 224×224 resolution (the paper's primary setting).
+
+| File | Model | Accuracy (%) | F1 |
+|---|---|---|---|
+| `GoldFormer_best.pth` | GoldFormer (CNN + Swin-T + TAAG) | **95.02 ± 0.75** | **0.9502** |
+| `ViT_B16_best.pth` | ViT-B/16 | 94.31 ± 0.94 | 0.9431 |
+| `Swin_T_best.pth` | Swin Transformer-Tiny (GoldFormer's backbone) | 93.65 ± 0.67 | 0.9365 |
+| `ResNet101_best.pth` | ResNet-101 | 92.29 ± 1.01 | 0.9228 |
+| `ResNet50_best.pth` | ResNet-50 | — | — |
+| `ResNet18_best.pth` | ResNet-18 | — | — |
+| `DenseNet121_best.pth` | DenseNet-121 | — | — |
+| `EfficientNet_B3_best.pth` | EfficientNet-B3 | — | — |
+| `EfficientNet_B0_best.pth` | EfficientNet-B0 | — | — |
+| `MobileNet_V2_best.pth` | MobileNet-V2 | — | — |
+
+GoldFormer is the best single model and beats a soft-voting ensemble (94.92%); it is
+statistically tied with the strongest individual backbone, ViT-B/16 (paired McNemar
+p = 0.228), and significantly beats its own Swin-T backbone (p = 0.014), while using
+about half ViT-B/16's FLOPs (8.6 vs 16.9 GFLOPs) and fewer parameters (54.3M vs 86.6M).
+
+All models trained with 5-fold stratified cross-validation, AdamW, AMP (bfloat16),
+freeze-then-unfreeze fine-tuning on the GoldNet dataset (2,127 images, 1,044
+authentic / 1,083 counterfeit).
 
 ## Usage
 
 ```python
 import torch
-from torchvision import transforms
-from PIL import Image
+from models import build_model   # models.py from the GitHub repo
 
 # Download weights
 # bash fetch_weights.sh   (from the GitHub repo)
 
-# Load a checkpoint
-model = torch.load("weights/GoldFormer_best.pth", weights_only=True)
+model = build_model("goldformer")
+state = torch.load("weights/GoldFormer_best.pth", map_location="cpu", weights_only=True)
+model.load_state_dict(state)   # strict — exact match with the released checkpoint
 model.eval()
 
+from torchvision import transforms
+from PIL import Image
+
 transform = transforms.Compose([
-    transforms.Resize((299, 299)),
+    transforms.Resize((224, 224)),
     transforms.ToTensor(),
     transforms.Normalize([0.485, 0.456, 0.406],
                          [0.229, 0.224, 0.225]),
@@ -67,24 +80,28 @@ img = Image.open("your_image.jpg").convert("RGB")
 x = transform(img).unsqueeze(0)
 
 with torch.no_grad():
-    logits = model(x)
+    logits, gamma = model(x)   # gamma = TAAG gate activations, for interpretability
     prob_authentic = torch.softmax(logits, dim=1)[0, 0].item()
     print(f"P(authentic) = {prob_authentic:.3f}")
 ```
 
-> **Note:** All baseline models use 224×224 input. GoldFormer uses 299×299.  
-> The `models.py` class definitions are in the [GitHub repo](https://github.com/zobeirraisi/GoldNet).
+> **Note:** All checkpoints, including GoldFormer, use 224×224 input in the published
+> configuration. The `models.py` class definitions (`TextureAwareAttentionGate` +
+> `GoldFormer`) are in the [GitHub repo](https://github.com/zobeirraisi/GoldNet).
 
 ## Citation
 
 ```bibtex
 @article{raisi2026goldformer,
-  title   = {GoldFormer: A Texture-Aware Vision Transformer-based Algorithm
+  title   = {GoldFormer: A Texture-Aware Vision Transformer-Based Algorithm
              for Detecting Near-Identical Images},
   author  = {Raisi, Zobeir},
   journal = {Algorithms},
+  volume  = {19},
+  number  = {7},
+  pages   = {530},
   year    = {2026},
-  note    = {Under review}
+  doi     = {10.3390/a19070530}
 }
 ```