Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Custom Dataset

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hallucination DetectionCustom Dataset
F1 Score72.9
15
Belief Dynamics PredictionCustom Dataset Belief Dynamics 1.0 (test)
Macro-Avg Precision (m1)39.7
9
GroundingCustom Dataset
mIoU25
8
Omission DetectionCustom Dataset
Accuracy64.5
7
Image ClassificationCustom Dataset 3
Accuracy0.9498
7
Image ClassificationCustom Dataset 2
Accuracy98.66
7
Self-ReenactmentCustom Dataset (test)
PSNR33.451
6
Cross-Object ReenactmentCustom Dataset (Ours) (test)
Hand Fidelity99.4
6
Change DetectionCustom Dataset Lab
Scan-wise IoU76.7
5
Change DetectionCustom Dataset Const-2F
Scan-wise IoU48.6
5
Change DetectionCustom Dataset Const-1F
Scan-wise IoU72.8
5
3D Velocity EstimationCustom Dataset (Scene 1)
AVE [m/s]0.22
4
Single-Concept GenerationCustom Single-Concept Dataset (test)
S^T_CLIP Score35.22
4
Stroke Guided Image SynthesisCustom dataset 800 image-prompt pairs
F(x, y)88.93
4
Autonomous DrivingCustom Dataset Dolphins
Metric-
0
Zero-day Ransomware DetectionCustom dataset Autoencoder
Accuracy-
0
Showing 16 of 16 rows