Home
Dataset
Results
Classification
Localization
Upload
TSWC2017
Information
Contact Name: Carl Lemaire
Email: carl.lemaire@usherbrooke.ca
Organization: Université de Sherbrooke
Method's Name: Inception V3
Reference: C.Szegedy, V.Vanhoucke, S.Ioffe, J.Shlens. Rethinking the inception architecture for computer vision. roceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2818-2826).
Project Website:
Evaluation Metrics
Precision of each category :
$$ Pre_i = \frac{TP_i}{TP_i + FP_i}$$
Articulated Truck
Bicycle
Bus
Car
Motorcycle
Non-motorized Vehicle
Pedestrian
Pickup Truck
Single Unit Truck
Work Van
Background
0.7812
0.8281
0.9713
0.9808
0.9178
0.5473
0.9543
0.8978
0.6144
0.8411
0.9919
Recall of each category:
$$ Rec_i = \frac{TP_i}{TP_i + FN_i}$$
Articulated Truck
Bicycle
Bus
Car
Motorcycle
Non-motorized Vehicle
Pedestrian
Pickup Truck
Single Unit Truck
Work Van
Background
0.9231
0.8266
0.9066
0.9723
0.8121
0.3037
0.8665
0.9355
0.7781
0.7911
0.9903
Accuracy: 0.9618
$$ Acc = \frac{TP}{Number of Testing Images}$$
Mean Recall: 0.8278
$$ {mRec} = {\rm mean}({Rec_i})$$
Mean Precision: 0.8478
$$ {mPre} = {\rm mean}({Pre_i})$$
Cohen Kappa Score: 0.9408
Confusion Matrix (%):
Predicted
Articulated Truck
Bicycle
Bus
Car
Motorcycle
Non-motorized Vehicle
Pedestrian
Pickup Truck
Single Unit Truck
Work Van
Background
True
Articulated Truck
92.31
0.00
0.35
0.23
0.00
0.15
0.00
0.27
6.22
0.00
0.46
Bicycle
1.05
82.66
0.18
0.88
3.15
0.53
9.28
0.53
0.18
0.00
1.58
Bus
2.60
0.00
90.66
0.70
0.00
0.04
0.00
0.04
2.56
2.95
0.47
Car
0.18
0.00
0.02
97.23
0.00
0.02
0.00
1.85
0.08
0.35
0.27
Motorcycle
0.00
3.64
0.00
7.88
81.21
1.82
0.20
1.82
1.21
0.00
2.22
Non-motorized Vehicle
23.52
0.23
1.83
5.71
0.00
30.37
0.00
2.28
33.33
0.68
2.05
Pedestrian
0.45
4.79
0.00
1.73
1.09
0.51
86.65
0.13
0.13
0.06
4.47
Pickup Truck
0.39
0.00
0.02
4.89
0.00
0.08
0.00
93.55
0.85
0.13
0.09
Single Unit Truck
14.14
0.00
0.23
1.33
0.00
0.23
0.00
4.06
77.81
1.72
0.47
Work Van
0.78
0.00
0.33
14.45
0.00
0.00
0.00
2.44
2.73
79.11
0.17
Background
0.30
0.01
0.05
0.33
0.00
0.16
0.02
0.02
0.05
0.05
99.03