Object Detection on PASCAL VOC x4 scale 2012 (test)
36.7mAPIHR → T
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| IHR → TPipeline Variant=IHR → T, SR Method=Oracle (IHR), Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 36.7 | 0 | — | |
| SR4IR (SwinIR)Pipeline Variant=Ours, SR Method=SwinIR, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 33.9 | 0.239 | 24.38 | |
| SR4IR (EDSR)Pipeline Variant=Ours, SR Method=EDSR-baseline, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 32.4 | 0.275 | 23.94 | |
| S → T (SwinIR)Pipeline Variant=S → T, SR Method=SwinIR, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 31.5 | 0.309 | 25.13 | |
| S + T (SwinIR)Pipeline Variant=S + T, SR Method=SwinIR, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 31.4 | 0.331 | 23.94 | |
| S → T (EDSR)Pipeline Variant=S → T, SR Method=EDSR-baseline, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 30.3 | 0.336 | 24.62 | |
| T → S (SwinIR)Pipeline Variant=T → S, SR Method=SwinIR, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 29.7 | 0.284 | 23.59 | |
| S + T (EDSR)Pipeline Variant=S + T, SR Method=EDSR-baseline, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 28.3 | 0.354 | 23.71 | |
| ILR → TPipeline Variant=ILR → T, SR Method=Bilinear up, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 27.5 | 0.411 | 22.77 | |
| T → S (EDSR)Pipeline Variant=T → S, SR Method=EDSR-baseline, Task Network=Faster-RCNN, Backbone=MobileNetV32024.04 | 27.2 | 0.317 | 23.37 |