|
|
--- |
|
|
library_name: pytorch |
|
|
license: unlicense |
|
|
tags: |
|
|
- real_time |
|
|
- android |
|
|
pipeline_tag: image-segmentation |
|
|
|
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
# BGNet: Optimized for Mobile Deployment |
|
|
## Segment images in real-time on device |
|
|
|
|
|
|
|
|
BGNet or Boundary-Guided Network, is a model designed for camouflaged object detection. It leverages edge semantics to enhance the representation learning process, making it more effective at identifying objects that blend into their surroundings |
|
|
|
|
|
This model is an implementation of BGNet found [here](https://github.com/thograce/bgnet). |
|
|
|
|
|
|
|
|
More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/bgnet). |
|
|
|
|
|
### Model Details |
|
|
|
|
|
- **Model Type:** Model_use_case.semantic_segmentation |
|
|
- **Model Stats:** |
|
|
- Model checkpoint: BGNet |
|
|
- Input resolution: 416x416 |
|
|
- Number of parameters: 77.8M |
|
|
- Model size: 297 MB |
|
|
|
|
|
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|
|
|---|---|---|---|---|---|---|---|---| |
|
|
| BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 118.319 ms | 1 - 126 MB | NPU | -- | |
|
|
| BGNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 116.819 ms | 2 - 11 MB | NPU | -- | |
|
|
| BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 34.374 ms | 1 - 209 MB | NPU | -- | |
|
|
| BGNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 41.165 ms | 2 - 50 MB | NPU | -- | |
|
|
| BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 22.942 ms | 1 - 19 MB | NPU | -- | |
|
|
| BGNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 19.894 ms | 2 - 4 MB | NPU | -- | |
|
|
| BGNet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 118.319 ms | 1 - 126 MB | NPU | -- | |
|
|
| BGNet | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 116.819 ms | 2 - 11 MB | NPU | -- | |
|
|
| BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 23.032 ms | 1 - 19 MB | NPU | -- | |
|
|
| BGNet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 19.82 ms | 2 - 4 MB | NPU | -- | |
|
|
| BGNet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 37.993 ms | 1 - 99 MB | NPU | -- | |
|
|
| BGNet | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 34.723 ms | 2 - 19 MB | NPU | -- | |
|
|
| BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 23.229 ms | 1 - 20 MB | NPU | -- | |
|
|
| BGNet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 19.833 ms | 2 - 4 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 22.84 ms | 1 - 19 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 19.968 ms | 2 - 29 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 20.487 ms | 0 - 173 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.768 ms | 0 - 234 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 14.738 ms | 2 - 76 MB | NPU | -- | |
|
|
| BGNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 14.886 ms | 4 - 83 MB | NPU | -- | |
|
|
| BGNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 15.45 ms | 1 - 126 MB | NPU | -- | |
|
|
| BGNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 12.583 ms | 2 - 63 MB | NPU | -- | |
|
|
| BGNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 15.563 ms | 2 - 65 MB | NPU | -- | |
|
|
| BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 20.261 ms | 2 - 2 MB | NPU | -- | |
|
|
| BGNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 22.284 ms | 154 - 154 MB | NPU | -- | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## License |
|
|
* The license for the original implementation of BGNet can be found |
|
|
[here](This model's original implementation does not provide a LICENSE.). |
|
|
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) |
|
|
|
|
|
|
|
|
|
|
|
## References |
|
|
* [BGNet: Boundary-Guided Camouflaged Object Detection (IJCAI 2022)](https://arxiv.org/abs/2207.00794) |
|
|
* [Source Model Implementation](https://github.com/thograce/bgnet) |
|
|
|
|
|
|
|
|
|
|
|
## Community |
|
|
* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI. |
|
|
* For questions or feedback please [reach out to us](mailto:[email protected]). |
|
|
|
|
|
## Usage and Limitations |
|
|
|
|
|
Model may not be used for or in connection with any of the following applications: |
|
|
|
|
|
- Accessing essential private and public services and benefits; |
|
|
- Administration of justice and democratic processes; |
|
|
- Assessing or recognizing the emotional state of a person; |
|
|
- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics; |
|
|
- Education and vocational training; |
|
|
- Employment and workers management; |
|
|
- Exploitation of the vulnerabilities of persons resulting in harmful behavior; |
|
|
- General purpose social scoring; |
|
|
- Law enforcement; |
|
|
- Management and operation of critical infrastructure; |
|
|
- Migration, asylum and border control management; |
|
|
- Predictive policing; |
|
|
- Real-time remote biometric identification in public spaces; |
|
|
- Recommender systems of social media platforms; |
|
|
- Scraping of facial images (from the internet or otherwise); and/or |
|
|
- Subliminal manipulation |
|
|
|
