Submission: GDRNPPDet_PBR/ITODD

Download submission
Submission name
Submission time (UTC) Oct. 14, 2022, 12:16 p.m.
User zyMeteroid
Task 2D detection of seen objects
Dataset ITODD
Training model type None
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AP:0.593
AP50:0.732
AP75:0.671
AP_large:0.594
AP_medium:0.495
AP_small:-1.000
AR1:0.246
AR10:0.761
AR100:0.795
AR_large:0.817
AR_medium:0.589
AR_small:-1.000
average_time_per_image:0.082

Method: GDRNPPDet_PBR

User zyMeteroid
Publication Not yet
Implementation Pytorch, code can be found at https://github.com/shanice-l/gdrnpp_bop2022
Training image modalities RGB
Test image modalities RGB
Description

Authors: Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Bowen Fu, Jiwen Tang, Xiquan Liang, Jingyi Tang, Xiaotian Cheng, Yukang Zhang, Gu Wang, and Xiangyang Ji (Tsinghua University).

In the PBR setting, all models are trained only using the provided PBR synthetic data. We trained one model for each dataset.

GDRNPPDet was based on YOLOX. We used stronger data augmentation and ranger optimizer.

Computer specifications GPU RTX 3090; CPU AMD EPYC 7H12 64-Core Processor.