openforensics-ensemble / evaluation_report.json
adarshcod30's picture
v2: three-backbone ensemble with corruption-matched augmentation
44db0f5 verified
Raw
History Blame Contribute Delete
11.7 kB
{
"model": "/Users/adarsh/Desktop/Projects/OpenForensics/runs/v2/final.keras",
"threshold_sweep": [
{
"threshold": 0.05,
"accuracy": 0.874,
"real_called_fake": 4,
"fake_called_real": 248
},
{
"threshold": 0.1,
"accuracy": 0.9085,
"real_called_fake": 7,
"fake_called_real": 176
},
{
"threshold": 0.15,
"accuracy": 0.922,
"real_called_fake": 12,
"fake_called_real": 144
},
{
"threshold": 0.2,
"accuracy": 0.9325,
"real_called_fake": 17,
"fake_called_real": 118
},
{
"threshold": 0.25,
"accuracy": 0.9405,
"real_called_fake": 20,
"fake_called_real": 99
},
{
"threshold": 0.3,
"accuracy": 0.9435,
"real_called_fake": 23,
"fake_called_real": 90
},
{
"threshold": 0.35,
"accuracy": 0.9465,
"real_called_fake": 25,
"fake_called_real": 82
},
{
"threshold": 0.4,
"accuracy": 0.95,
"real_called_fake": 26,
"fake_called_real": 74
},
{
"threshold": 0.45,
"accuracy": 0.9515,
"real_called_fake": 32,
"fake_called_real": 65
},
{
"threshold": 0.5,
"accuracy": 0.951,
"real_called_fake": 39,
"fake_called_real": 59
},
{
"threshold": 0.55,
"accuracy": 0.9535,
"real_called_fake": 44,
"fake_called_real": 49
},
{
"threshold": 0.6,
"accuracy": 0.9535,
"real_called_fake": 48,
"fake_called_real": 45
},
{
"threshold": 0.65,
"accuracy": 0.95,
"real_called_fake": 59,
"fake_called_real": 41
},
{
"threshold": 0.7,
"accuracy": 0.949,
"real_called_fake": 66,
"fake_called_real": 36
},
{
"threshold": 0.75,
"accuracy": 0.944,
"real_called_fake": 81,
"fake_called_real": 31
},
{
"threshold": 0.8,
"accuracy": 0.939,
"real_called_fake": 95,
"fake_called_real": 27
},
{
"threshold": 0.85,
"accuracy": 0.9335,
"real_called_fake": 110,
"fake_called_real": 23
},
{
"threshold": 0.9,
"accuracy": 0.9235,
"real_called_fake": 137,
"fake_called_real": 16
},
{
"threshold": 0.95,
"accuracy": 0.8955,
"real_called_fake": 201,
"fake_called_real": 8
}
],
"manifest_digest": "c1e5955e936b52d4",
"tta": true,
"calibration": {
"temperature": 0.8760257766124369,
"val_ece_raw": 0.008403347671031909,
"val_ece_calibrated": 0.0033754417697588602
},
"operating_point": {
"criterion": "target_recall",
"target": 0.99,
"threshold": 0.36217108368873596,
"rationale": "Chosen on validation to hold recall on genuine images at 0.99. Youden and F1 both land near 0.761, which raises real-images-called-fake from 39 to 83 without improving accuracy. The full threshold_sweep ships alongside."
},
"test_at_0.5": {
"threshold": 0.5,
"accuracy": 0.951,
"roc_auc": 0.989896,
"pr_auc": 0.9899874925285668,
"confusion_matrix": [
[
941,
59
],
[
39,
961
]
],
"real_called_fake": 39,
"fake_called_real": 59,
"false_accusation_rate": 0.039,
"ece": 0.007834798693656874,
"n": 2000,
"fake_recall": 0.941,
"real_recall": 0.961
},
"test_at_threshold": {
"threshold": 0.36217108368873596,
"accuracy": 0.948,
"roc_auc": 0.989896,
"pr_auc": 0.9899874925285668,
"confusion_matrix": [
[
921,
79
],
[
25,
975
]
],
"real_called_fake": 25,
"fake_called_real": 79,
"false_accusation_rate": 0.025,
"ece": 0.007834798693656874,
"n": 2000,
"fake_recall": 0.921,
"real_recall": 0.975
},
"risk_coverage": [
{
"coverage": 1.0,
"n": 2000,
"accuracy": 0.951,
"min_confidence": 0.5005548000335693
},
{
"coverage": 0.953,
"n": 1905,
"accuracy": 0.9690288713910761,
"min_confidence": 0.6960272789001465
},
{
"coverage": 0.905,
"n": 1810,
"accuracy": 0.9773480662983426,
"min_confidence": 0.824684739112854
},
{
"coverage": 0.858,
"n": 1715,
"accuracy": 0.9860058309037901,
"min_confidence": 0.8969419002532959
},
{
"coverage": 0.811,
"n": 1621,
"accuracy": 0.9907464528069093,
"min_confidence": 0.9355311989784241
},
{
"coverage": 0.763,
"n": 1526,
"accuracy": 0.9927916120576671,
"min_confidence": 0.9599580764770508
},
{
"coverage": 0.716,
"n": 1431,
"accuracy": 0.9937106918238994,
"min_confidence": 0.9731913805007935
},
{
"coverage": 0.668,
"n": 1336,
"accuracy": 0.9940119760479041,
"min_confidence": 0.981025755405426
},
{
"coverage": 0.621,
"n": 1242,
"accuracy": 0.9943639291465378,
"min_confidence": 0.986376166343689
},
{
"coverage": 0.574,
"n": 1147,
"accuracy": 0.997384481255449,
"min_confidence": 0.9896464943885803
},
{
"coverage": 0.526,
"n": 1052,
"accuracy": 0.9990494296577946,
"min_confidence": 0.992717444896698
},
{
"coverage": 0.479,
"n": 957,
"accuracy": 0.9989550679205852,
"min_confidence": 0.9947149753570557
},
{
"coverage": 0.432,
"n": 863,
"accuracy": 0.9988412514484357,
"min_confidence": 0.9961569905281067
},
{
"coverage": 0.384,
"n": 768,
"accuracy": 0.9986979166666666,
"min_confidence": 0.9970833659172058
},
{
"coverage": 0.337,
"n": 673,
"accuracy": 0.9985141158989599,
"min_confidence": 0.99782794713974
},
{
"coverage": 0.289,
"n": 578,
"accuracy": 1.0,
"min_confidence": 0.9984116554260254
},
{
"coverage": 0.242,
"n": 484,
"accuracy": 1.0,
"min_confidence": 0.9988195300102234
},
{
"coverage": 0.195,
"n": 389,
"accuracy": 1.0,
"min_confidence": 0.9991379976272583
},
{
"coverage": 0.147,
"n": 294,
"accuracy": 1.0,
"min_confidence": 0.9994103908538818
},
{
"coverage": 0.1,
"n": 200,
"accuracy": 1.0,
"min_confidence": 0.9996227025985718
}
],
"per_corruption": {
"clean": {
"threshold": 0.7607657313346863,
"accuracy": 0.9405,
"roc_auc": 0.9898959999999999,
"pr_auc": 0.9899874874900219,
"confusion_matrix": [
[
973,
27
],
[
92,
908
]
],
"real_called_fake": 92,
"fake_called_real": 27,
"false_accusation_rate": 0.092,
"ece": 0.01360419222712515,
"n": 2000,
"fake_recall": 0.973,
"real_recall": 0.908
},
"desaturate": {
"threshold": 0.7607657313346863,
"accuracy": 0.9255,
"roc_auc": 0.9873709999999999,
"pr_auc": 0.987042223907956,
"confusion_matrix": [
[
976,
24
],
[
125,
875
]
],
"real_called_fake": 125,
"fake_called_real": 24,
"false_accusation_rate": 0.125,
"ece": 0.012363795459270471,
"n": 2000,
"fake_recall": 0.976,
"real_recall": 0.875
},
"colour_cast": {
"threshold": 0.7607657313346863,
"accuracy": 0.923,
"roc_auc": 0.9873129999999999,
"pr_auc": 0.9875305928718285,
"confusion_matrix": [
[
978,
22
],
[
132,
868
]
],
"real_called_fake": 132,
"fake_called_real": 22,
"false_accusation_rate": 0.132,
"ece": 0.010169397294521293,
"n": 2000,
"fake_recall": 0.978,
"real_recall": 0.868
},
"gaussian_noise": {
"threshold": 0.7607657313346863,
"accuracy": 0.9105,
"roc_auc": 0.982704,
"pr_auc": 0.9828172399928267,
"confusion_matrix": [
[
965,
35
],
[
144,
856
]
],
"real_called_fake": 144,
"fake_called_real": 35,
"false_accusation_rate": 0.144,
"ece": 0.008556965082883835,
"n": 2000,
"fake_recall": 0.965,
"real_recall": 0.856
},
"speckle": {
"threshold": 0.7607657313346863,
"accuracy": 0.8745,
"roc_auc": 0.978552,
"pr_auc": 0.9775095733546318,
"confusion_matrix": [
[
976,
24
],
[
227,
773
]
],
"real_called_fake": 227,
"fake_called_real": 24,
"false_accusation_rate": 0.227,
"ece": 0.012776412010192894,
"n": 2000,
"fake_recall": 0.976,
"real_recall": 0.773
},
"blur": {
"threshold": 0.7607657313346863,
"accuracy": 0.9025,
"roc_auc": 0.9797769999999999,
"pr_auc": 0.9788085527230819,
"confusion_matrix": [
[
960,
40
],
[
155,
845
]
],
"real_called_fake": 155,
"fake_called_real": 40,
"false_accusation_rate": 0.155,
"ece": 0.01519329649209979,
"n": 2000,
"fake_recall": 0.96,
"real_recall": 0.845
},
"jpeg_artifact": {
"threshold": 0.7607657313346863,
"accuracy": 0.926,
"roc_auc": 0.985421,
"pr_auc": 0.9849191247097082,
"confusion_matrix": [
[
966,
34
],
[
114,
886
]
],
"real_called_fake": 114,
"fake_called_real": 34,
"false_accusation_rate": 0.114,
"ece": 0.010649448722600941,
"n": 2000,
"fake_recall": 0.966,
"real_recall": 0.886
},
"pixelate": {
"threshold": 0.7607657313346863,
"accuracy": 0.8725,
"roc_auc": 0.9622930000000001,
"pr_auc": 0.9616763347010586,
"confusion_matrix": [
[
943,
57
],
[
198,
802
]
],
"real_called_fake": 198,
"fake_called_real": 57,
"false_accusation_rate": 0.198,
"ece": 0.03926752486824989,
"n": 2000,
"fake_recall": 0.943,
"real_recall": 0.802
},
"brightness_shift": {
"threshold": 0.7607657313346863,
"accuracy": 0.921,
"roc_auc": 0.986505,
"pr_auc": 0.9866079174092961,
"confusion_matrix": [
[
975,
25
],
[
133,
867
]
],
"real_called_fake": 133,
"fake_called_real": 25,
"false_accusation_rate": 0.133,
"ece": 0.01671682763099669,
"n": 2000,
"fake_recall": 0.975,
"real_recall": 0.867
},
"occlusion": {
"threshold": 0.7607657313346863,
"accuracy": 0.93,
"roc_auc": 0.985571,
"pr_auc": 0.9846328275987414,
"confusion_matrix": [
[
968,
32
],
[
108,
892
]
],
"real_called_fake": 108,
"fake_called_real": 32,
"false_accusation_rate": 0.108,
"ece": 0.019010440915823004,
"n": 2000,
"fake_recall": 0.968,
"real_recall": 0.892
}
},
"distribution_shift": {
"recall_real_val_at_0.5": 0.986,
"recall_real_test_at_0.5": 0.961,
"p10_real_scores_val": 0.9771469235420227,
"p10_real_scores_test": 0.8302948474884033
}
}