ChaoningZhang / MobileSAM

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
Apache License 2.0
4.79k stars 500 forks source link

Performance comparison of Mobile SAM and SAM-Base #108

Open Nastu-Ho opened 1 year ago

Nastu-Ho commented 1 year ago

Will mobile SAM have better segmentation accuracy than SAM-Base?

ryouchinsa commented 1 year ago

Thanks for using MobileSAM. We can answer your question.

MobileSAM was trained on auto generated annotations in Segment Anything 1 Billion (SA-1B) dataset. So that the mask area when you click a foreground point tends to be large. But, if you click multiple foreground/background points, the accuracy is almost the same as ViT-Base SAM.

The model size of MobileSAM is smaller so that the calculation speed is faster. We used the quantized ViT-Base SAM model as comparison.

28.1MB mobile_sam_preprocess.onnx 16.5MB mobile_sam.onnx

108.9MB sam_vit_b_01ec64_preprocess.onnx 8.8MB sam_vit_b_01ec64.onnx

When click a foreground point using MobileSAM.

スクリーンショット 2023-10-24 4 23 06

When click a foreground point using ViT-Base SAM.

スクリーンショット 2023-10-24 4 23 25