Skip to content

[Reimplementation] Not able to reimplement the final performance #6

@Sino0904

Description

@Sino0904

Prerequisite

💬 Describe the reimplementation questions

I tried to re-implement the GOOD results for voc-to-nonvoc setting and I am getting a lower performance. I trainied bot the stages from scratch following the instructions (i.e. generated depth and normal images, trained stage1 and stage 2). Here are the final results:

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.041
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.064
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.040
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.026
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.051
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.073
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.173
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.243
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 30 ] = 0.284
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 50 ] = 0.336
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.388
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=300 ] = 0.448
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=500 ] = 0.469
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.220
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.472
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.611

As you can see, the AR@100 is 0.5% lower than what is reported in the paper. On comparing pseudoboxes that I get from stage 1 to the provided pseudoboxes, there are some differences. Is there a way to replicate stage-1 output?

Thanks!

Environment

Followed the same environment as given in the instructions.

Expected results

No response

Additional information

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions