Object Detection on 1 Mpx (test)
48.4mAPGET-T
Evaluation Results
| Method | Links | |
|---|---|---|
| GET-TBackbone=Transformer + RNN, Detection Head=YOLOX, Runtime (ms)=18.2, Parameters (M)=21.92024.02 | 48.4 | |
| ASTMNetBackbone=(T)CNN + RNN, Detection Head=SSD, Time (ms)=72.3, Params (M)=> 100*2022.12 | 48.3 | |
| ASTMNetTime (ms)=72.3, Size (M)=> 1002023.11 | 48.3 | |
| S5-ViT-BBackbone=Transformer + SSM, Detection Head=YOLOX, Runtime (ms)=9.57, Parameters (M)=18.22024.02 | 47.8 | |
| RVT-BBackbone=Transformer + RNN, Detection Head=YOLOX [15], Time (ms)=11.9 (6.1), Params (M)=18.52022.12 | 47.4 | |
| RVT-BTime (ms)=11.9, Size (M)=18.52023.11 | 47.4 | |
| RVT-BBackbone=Transformer + RNN, Detection Head=YOLOX, Runtime (ms)=11.9, Parameters (M)=18.52024.02 | 47.4 | |
| S4D-ViT-BBackbone=Transformer + SSM, Detection Head=YOLOX, Runtime (ms)=10.9, Parameters (M)=16.52024.02 | 46.8 | |
| LEOD-RVT-STime (ms)=10.1, Size (M)=9.92023.11 | 46.7 | |
| S5-ViT-SBackbone=Transformer + SSM, Detection Head=YOLOX, Runtime (ms)=8.87, Parameters (M)=9.72024.02 | 46.5 | |
| Swin-T v2Backbone=Transformer + RNN, Detection Head=YOLOX, Runtime (ms)=34.5, Parameters (M)=21.12024.02 | 46.4 | |
| Nested-TBackbone=Transformer + RNN, Detection Head=YOLOX, Runtime (ms)=33.5, Parameters (M)=22.22024.02 | 46 | |
| RVT-SBackbone=Transformer + RNN, Detection Head=YOLOX, Time (ms)=10.1 (5.0), Params (M)=9.92022.12 | 44.1 | |
| RVT-STime (ms)=10.1, Size (M)=9.92023.11 | 44.1 | |
| REDBackbone=CNN + RNN, Detection Head=SSD, Time (ms)=39.3, Params (M)=24.12022.12 | 43 | |
| REDTime (ms)=39.3, Size (M)=24.12023.11 | 43 | |
| REDBackbone=CNN + RNN, Detection Head=SSD, Runtime (ms)=39.3, Parameters (M)=24.12024.02 | 43 | |
| RVT-TBackbone=Transformer + RNN, Detection Head=YOLOX, Time (ms)=9.5 (3.5), Params (M)=4.42022.12 | 41.5 | |
| ERGO-12Time (ms)=101.1, Size (M)=59.6, Backbone=Swin Transformer V22023.11 | 40.6 | |
| ERGO-12Backbone=Transformer, Detection Head=YOLOv6, Runtime (ms)=100.0, Parameters (M)=59.62024.02 | 40.6 | |
| YOLOv3 EventsBackbone=CNN, Detection Head=YOLOV3, Time (ms)=49.4, Params (M)=> 60*2022.12 | 34.6 | |
| YOLOv3 EventsBackbone=CNN, Detection Head=YOLOv3, Runtime (ms)=49.4, Parameters (M)=> 60*2024.02 | 34.6 | |
| RRC-EventsBackbone=CNN, Detection Head=YOLOv3 [41], Time (ms)=46.4, Params (M)=> 100*2022.12 | 34.3 | |
| RRC-EventsBackbone=CNN, Detection Head=YOLOv3, Runtime (ms)=46.4, Parameters (M)=> 100*2024.02 | 34.3 | |
| Inception + SSDBackbone=CNN, Detection Head=SSD, Time (ms)=45.2, Params (M)=> 60*2022.12 | 34 | |
| Inception + SSDBackbone=CNN, Detection Head=SSD, Runtime (ms)=45.2, Parameters (M)=> 60*2024.02 | 34 |