Add historical and museum calibration (#3)

- Upload 10 files (1e36fec5ecdb02e59d72ac5735fd69450d537c43)
- chore remove unsued folder/files (b6c691f49684e270df414de4ebf0e171e8b30cef)


Co-authored-by: Anjith George <anjith2006@users.noreply.huggingface.co>

app.py

@@ -10,6 +10,7 @@ from __future__ import annotations
 import os
 import time
 from functools import lru_cache
+from collections.abc import Callable
 
 import numpy as np
 import pandas as pd
@@ -23,6 +24,7 @@ from lib.models import get_model
 from lib.align import get_preprocessor
 
 from calibrate_score import (
+    fit_calibrator_from_csv,
     fit_calibrator_from_scores,
     apply_calibrator,
 )
@@ -39,15 +41,17 @@ DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 PROJECT_URL = "https://www.idiap.ch/paper/artface/"
 ARXIV_URL = "https://arxiv.org/abs/2508.20626"
 
-CALIBRATION_DIR = "calibration"
-
-CALIBRATION_FILES = {
-    "clip": os.path.join(CALIBRATION_DIR, "clip.csv"),
-    "lora": os.path.join(CALIBRATION_DIR, "lora.csv"),
-    "ires100": os.path.join(CALIBRATION_DIR, "ires100.csv"),
-    "ires100-tune": os.path.join(CALIBRATION_DIR, "ires100-tune.csv"),
+DATASET_DIRS = {
+    "Historical Faces": "historicalface",
+    "Museum": "museum",
 }
 
+def get_calibration_files(folder):
+    return {
+        model: os.path.join(folder, f"{model}.csv")
+        for model in MODEL_VARIANTS
+    }
+
 # =====================================================
 # Original Palette & Friendly Professional Styling
 # =====================================================
@@ -199,7 +203,7 @@ TITLE_HTML = f"""
 """
 
 # =====================================================
-# Backend (Same functionality)
+# Backend
 # =====================================================
 
 aligner = get_preprocessor("align")
@@ -211,22 +215,18 @@ for name in MODEL_VARIANTS:
 
 
 @lru_cache(maxsize=None)
-def get_cached_dynamic_calibrator(selected_models_key, fuse_method):
+def get_cached_dynamic_calibrator(selected_models_key, fuse_method, cal_folder):
     selected_models = list(selected_models_key)
+    calibration_files = get_calibration_files(cal_folder)
     key_cols = ["probe_subject_id", "bio_ref_subject_id"]
     merged = None
     for name in selected_models:
-        df = pd.read_csv(CALIBRATION_FILES[name])[key_cols + ["score"]].rename(
-            columns={"score": f"score_{name}"}
-        )
+        df = pd.read_csv(calibration_files[name])[key_cols + ["score"]].rename(columns={"score": f"score_{name}"})
         merged = df if merged is None else merged.merge(df, on=key_cols, how="inner")
 
     score_cols = [f"score_{name}" for name in selected_models]
-    labels = (
-        (merged["probe_subject_id"] == merged["bio_ref_subject_id"]).astype(int).values
-    )
+    labels = (merged["probe_subject_id"] == merged["bio_ref_subject_id"]).astype(int).values
 
-    # Simple manual fusion for the cohort
     scores_mat = merged[score_cols].values
     if fuse_method == "median":
         fused = np.median(scores_mat, axis=1)
@@ -246,87 +246,57 @@ def make_plot(cal, target_score):
     target_llr = ((w * target_score) + b) / np.log(10)
 
     fig, ax = plt.subplots(figsize=(9, 5), facecolor=BG)
-    # Frequency histogram (not density)
-    ax.hist(
-        llrs[cal["cohort_labels"] == 1],
-        bins=40,
-        alpha=0.6,
-        label="Genuines",
-        color="tab:blue",
-        orientation="horizontal",
-        density=True,
-    )
-    ax.hist(
-        llrs[cal["cohort_labels"] == 0],
-        bins=40,
-        alpha=0.6,
-        label="Impostors",
-        color="tab:orange",
-        orientation="horizontal",
-        density=True,
-    )
-
-    ax.axhline(target_llr, color=TEXT, lw=3, ls="--", label=f"Result: {target_llr:.2f}")
+    ax.hist(llrs[cal["cohort_labels"] == 1], bins=40, alpha=0.6, label="Genuines", color="tab:blue", orientation='horizontal', density=True)
+    ax.hist(llrs[cal["cohort_labels"] == 0], bins=40, alpha=0.6, label="Impostors", color="tab:orange", orientation='horizontal', density=True)
+
+    ax.axhline(target_llr, color=TEXT, lw=3, ls='--', label=f"Result: {target_llr:.2f}")
 
     yticks = [-7, -5, -3, -1, 0, 1, 3, 5, 7]
-    ylabs = [
-        "Extreme $H_I$",
-        "V.Strong $H_I$",
-        "Strong $H_I$",
-        "Weak $H_I$",
-        "Neutral",
-        "Weak $H_G$",
-        "Strong $H_G$",
-        "V.Strong $H_G$",
-        "Extreme $H_G$",
-    ]
+    ylabs = ["Extreme $H_I$", "V.Strong $H_I$", "Strong $H_I$", "Weak $H_I$", "Neutral", "Weak $H_G$", "Strong $H_G$", "V.Strong $H_G$", "Extreme $H_G$"]
     ax.set_yticks(yticks)
     ax.set_yticklabels(ylabs, fontsize=9)
     ax.set_ylim([-8, 8])
     ax.set_ylabel("ENFSI Verbal Scale")
     ax.set_xlabel("Frequency (Counts)")
-    ax.set_title(
-        "Calibrated Likelihood Distribution (Cohort Counts)", fontweight="bold"
-    )
-    ax.grid(axis="y", alpha=0.2)
+    ax.set_title("Calibrated Likelihood Distribution (Cohort Counts)", fontweight="bold")
+    ax.grid(axis='y', alpha=0.2)
     ax.legend(frameon=False, loc="upper right")
     plt.tight_layout()
     return fig
 
 
-def process(img1, img2, models, method):
+def process(img1, img2, models, method, cal_dataset):
     if not img1 or not img2:
         return [None] * 4 + [pd.DataFrame()]
     a1, a2 = aligner(img1), aligner(img2)
     if not a1 or not a2:
         return [None] * 2 + ["No face detected", None, pd.DataFrame()]
 
+    cal_folder = DATASET_DIRS[cal_dataset]
+
     start = time.time()
     scores = {}
     for n in models:
         m, prep = MODELS[n]
-        x1, x2 = prep(a1).unsqueeze(0).to(DEVICE), prep(a2).unsqueeze(0).to(DEVICE)
+        x1 = prep(a1).unsqueeze(0).to(DEVICE)
+        x2 = prep(a2).unsqueeze(0).to(DEVICE)
         with torch.no_grad():
             e1, e2 = m(x1)[0].cpu().numpy(), m(x2)[0].cpu().numpy()
-        scores[n] = float(
-            np.dot(e1, e2) / (np.linalg.norm(e1) * np.linalg.norm(e2) + 1e-12)
-        )
-
-    f_score = (
-        np.mean(list(scores.values()))
-        if method == "mean"
-        else (
-            np.median(list(scores.values()))
-            if method == "median"
-            else np.max(list(scores.values()))
-        )
-    )
+        scores[n] = float(np.dot(e1, e2) / (np.linalg.norm(e1) * np.linalg.norm(e2) + 1e-12))
+
+    if method == "mean":
+        f_score = np.mean(list(scores.values()))
+    elif method == "median":
+        f_score = np.median(list(scores.values()))
+    else:
+        f_score = np.max(list(scores.values()))
+
     dur = time.time() - start
 
     try:
-        cal = get_cached_dynamic_calibrator(tuple(sorted(models)), method)
+        cal = get_cached_dynamic_calibrator(tuple(sorted(models)), method, cal_folder)
         res = apply_calibrator(f_score, cal)
-        llr_val, interp = res["llr_10"], res["interpretation"]
+        llr_val, interp = res['llr_10'], res['interpretation']
         plot = make_plot(cal, f_score)
     except Exception as e:
         llr_val, interp, plot = 0.0, f"Error: {str(e)}", None
@@ -339,7 +309,7 @@ def process(img1, img2, models, method):
       <div>
         <div class="fused-title">Likelihood Ratio (Log₁₀)</div>
         <div class="fused-meta">
-          Method: <b>{method}</b> · Models: {len(models)} · ⏱ {dur:.2f}s<br>
+          Method: <b>{method}</b> · Models: {len(models)} · Dataset: <b>{cal_dataset}</b> · ⏱ {dur:.2f}s<br>
           <span class="pill" style="background:{pill_bg}; color:{pill_tx};">Verdict: {interp}</span>
         </div>
       </div>
@@ -355,7 +325,7 @@ def process(img1, img2, models, method):
 
 
 # =====================================================
-# UI (Original Column Style)
+# UI
 # =====================================================
 
 with gr.Blocks(title="ArtFace") as demo:
@@ -363,9 +333,7 @@ with gr.Blocks(title="ArtFace") as demo:
         gr.HTML(TITLE_HTML)
 
         with gr.Group():
-            gr.HTML(
-                '<div class="section-h">Inputs</div><div class="hint">Upload Reference and Probe images for alignment and identification.</div>'
-            )
+            gr.HTML('<div class="section-h">Inputs</div><div class="hint">Upload Reference and Probe images for alignment and identification.</div>')
             with gr.Row():
                 i1 = gr.Image(label="Image A", type="pil", height=300)
                 i2 = gr.Image(label="Image B", type="pil", height=300)
@@ -375,40 +343,34 @@ with gr.Blocks(title="ArtFace") as demo:
                 clear = gr.ClearButton([i1, i2], value="Clear")
 
         with gr.Accordion("Analysis Settings", open=False):
-            sel = gr.CheckboxGroup(
-                MODEL_VARIANTS, value=["lora"], label="Active Models"
-            )
-            met = gr.Radio(
-                ["mean", "median", "max"], value="mean", label="Fusion Method"
+            sel = gr.CheckboxGroup(MODEL_VARIANTS, value=["lora", "ires100-tune", "ires100"], label="Active Models")
+            met = gr.Radio(["mean", "median", "max"], value="mean", label="Fusion Method")
+            cal_dir = gr.Dropdown(
+                choices=list(DATASET_DIRS.keys()),
+                value="Historical Faces",
+                label="Calibration Dataset",
             )
 
         gr.HTML('<div style="height:1px; background:#E7E7EA; margin: 1.5rem 0;"></div>')
 
-        gr.HTML(
-            '<div class="section-h">Results</div><div class="hint">Calibrated LLR based on ENFSI standards.</div>'
-        )
+        gr.HTML('<div class="section-h">Results</div><div class="hint">Calibrated LLR based on ENFSI standards.</div>')
 
         with gr.Row():
             o1 = gr.Image(label="Aligned A", height=150, interactive=False)
             o2 = gr.Image(label="Aligned B", height=150, interactive=False)
 
-        res_html = gr.HTML(
-            '<div style="padding:1rem; text-align:center; color:#556070;">Execute analysis to see likelihood score.</div>'
-        )
+        res_html = gr.HTML('<div style="padding:1rem; text-align:center; color:#556070;">Execute analysis to see likelihood score.</div>')
 
         with gr.Row():
             res_table = gr.Dataframe(label="Individual Scores", interactive=False)
             res_plot = gr.Plot(label="Likelihood Distribution")
 
-        gr.HTML(
-            '<div class="footer">Research Demo · Idiap Research Institute · 2026</div>'
-        )
+        gr.HTML('<div class="footer">Research Demo · Idiap Research Institute · 2026</div>')
 
-    run.click(process, [i1, i2, sel, met], [o1, o2, res_html, res_plot, res_table])
+    run.click(process, [i1, i2, sel, met, cal_dir], [o1, o2, res_html, res_plot, res_table])
 
 if __name__ == "__main__":
     demo.launch(
         theme=gr.themes.Soft(primary_hue="orange", neutral_hue="slate"),
-        css=CSS,
-        share=True,
-    )
+        css=CSS, share=True,
+    )

museum/clip.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf94347de725e9a224eb1a6a85d552a2aa588b32c46123033d6b5af5f24c044f
+size 441370

museum/ires100-tune.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf596b9457652fcf24cc165f6c23b0a185f8270ce025bde68ad6fce1e7dfe6d
+size 446220

museum/ires100.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a9ad6f73162e595665fd83cb772d612f7d5e482ebef69afe64f890537039bb
+size 444890

museum/lora.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad8555c44492c3182903c3670646b6c087a3d762707c419a88898de62a85755
+size 443032