chanchanchan97 / ICAFusion

ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection, Pattern Recognition
GNU Affero General Public License v3.0
94 stars 7 forks source link

作者提供的权重在FLIR上的mAP50指标直接val是0.828,和论文里的指标对应不上 #18

Closed CarryHJR closed 4 months ago

CarryHJR commented 4 months ago

直接运行 python test.py --weights weights/ICAFusion_FLIR.pt --device 1

 Class      Images      Labels           P           R      mAP@.5     mAP@.75  mAP@.5:.95: 100%|█████████████████████████████| 1013/1013 [00:58<00:00, 17.42it/s]
                 all        1013        8588       0.813       0.769       0.828       0.338       0.407
              MR-all     MR-day   MR-night    MR-near  MR-medium     MR-far    MR-none MR-partial   MR-heavy Recall-all
                0.00       0.00       0.00       0.00       0.00       0.00       0.00       0.00       0.00       0.00
              person        1013        4106       0.834       0.766       0.849       0.287       0.385
                 car        1013        4123       0.836       0.847       0.898       0.603       0.552
             bicycle        1013         359       0.768       0.693       0.738       0.124       0.283
CarryHJR commented 4 months ago

个人推测 可能作者论文实验里面的划分 和 上传权重对应的划分不一致,论文里面在FLIR上 mAP50是 79.2

chanchanchan97 commented 4 months ago

我们一直在优化代码框架,所以目前的实际性能与论文会有所不同。但是融合模块的代码与论文中提出的方法仍然是保持一致的。 We continuously optimize our codes, which results in the difference in detection performance. However, the codes of module for multimodal feature fusion still remain consistent with the methods proposed in this paper.