How is the performance on Pascal VOC？

[MingXiangL]

❔How is the performance on Pascal VOC？

Hi, I test YOLOS on pascal voc 2007 with default parameters, I can't get a satisfactory result, here is my result：

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.276 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.497 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.274 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.006 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.085 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.390 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.297 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.433 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.490 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.053 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.289 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.628

I wonder is there anything go wrong, could you give me some advice?

Additional context

[LegendBC]

Hi @StillWaterRUN , thanks for your interest in YOLOS.

We haven't tried VOC2007, so can you provide more details about your training? (model size, how many epochs you run, from scratch or finetune)

[MingXiangL]

I think the small amount of data of VOC2007 should be responsible for the performance.

[Yuxin-CV]

We believe we have answered your question, and as such I'm closing this issue, but let us know if you have further questions.

[hyunOO]

Hello @StillWaterRUN , could you share the configurations of the experiments (e.g, the architecture you used, which checkpoint you started to train, types of augmentations, # of detection tokens ... ) you conducted on VOC 2007?