Small Object Detection
Small Object Detection is a computer vision task that involves detecting and localizing small objects in images or videos. This task is challenging due to the small size and low resolution of the objects, as well as other factors such as occlusion, background clutter, and variations in lighting conditions.
( Image credit: Feature-Fused SSD )
Papers
Showing 1–10 of 152 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Weighted Box Fusion (WBF) | AP50 | 30.3 | — | Unverified |
| 2 | GFL + Test Time Augmentation | AP50 | 23.7 | — | Unverified |
| 3 | DL method (YOLOv8 + Ensamble) | AP50 | 22.9 | — | Unverified |
| 4 | Swin Transformer + Hierarchical design | AP50 | 22.6 | — | Unverified |
| 5 | E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet) | AP50 | 22.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Weighted Box Fusion (WBF) | AP50 | 77.6 | — | Unverified |
| 2 | GFL + Test Time Augmentation | AP50 | 73.1 | — | Unverified |
| 3 | DL method (YOLOv8 + Ensamble) | AP50 | 73.1 | — | Unverified |
| 4 | Swin Transformer + Hierarchical design | AP50 | 70.2 | — | Unverified |
| 5 | E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet) | AP50 | 69.6 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | BeeDetector | Average F1 | 0.86 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CFINet | [email protected]:0.95 | 30.7 | — | Unverified |