Mask2Former: Optimized for Qualcomm Devices

Mask2Former is a machine learning model that predicts masks and classes of objects in an image.

This is based on the implementation of Mask2Former found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS8450 (Proxy)	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit Mask2Former on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Mask2Former on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Model checkpoint: facebook/mask2former-swin-tiny-coco-panoptic
• Input resolution: 384x384
• Number of output classes: 100

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	69.161 ms	2 - 11 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	87.57 ms	2 - 11 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	69.566 ms	2 - 2 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	143.976 ms	2 - 2 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	143.976 ms	2 - 2 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	103.137 ms	2 - 9 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	142.507 ms	2 - 3 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	145.261 ms	2 - 10 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	145.261 ms	2 - 10 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	145.261 ms	2 - 10 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	184.612 ms	2 - 7 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	144.854 ms	2 - 9 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	87.57 ms	2 - 11 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8450 (Proxy)	230.38 ms	2 - 11 MB	NPU
Mask2Former	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	276.505 ms	2 - 10 MB	NPU

License

• The license for the original implementation of Mask2Former can be found here.

References

• Masked-attention Mask Transformer for Universal Image Segmentation
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.