Qualcomm® AI HubAI Hub

MaskRCNN

Instance segmentation for object detection and masking.

Mask R‑CNN is a machine learning model that extends Faster R‑CNN to perform instance segmentation by detecting objects in an image while simultaneously generating a high‑quality segmentation mask for each instance. It adds a branch for predicting segmentation masks in parallel with the existing branch for bounding box recognition.

Model RepositoryHugging FaceResearch Paper

Technical Details

Model checkpoint:Mask R-CNN ResNet-50 FPN V2
Input resolution:800x800
Number of output classes:91
Number of parameters:46.4M
Model size (float):177 MB

Applicable Scenarios

  • Factory Automation
  • Robotic Navigation
  • Camera

Supported Form Factors

  • Phone
  • Tablet
  • IoT
  • XR

License

Model:BSD-3-CLAUSE

Supported Devices

  • QCS8275 (Proxy)
  • QCS8450 (Proxy)
  • QCS8550 (Proxy)
  • SA7255P ADP
  • SA8295P ADP
  • SA8775P ADP
  • Samsung Galaxy S21
  • Samsung Galaxy S21 Ultra
  • Samsung Galaxy S21+
  • Samsung Galaxy S22 5G
  • Samsung Galaxy S22 Ultra 5G
  • Samsung Galaxy S22+ 5G
  • Samsung Galaxy S23
  • Samsung Galaxy S23 Ultra
  • Samsung Galaxy S23+
  • Samsung Galaxy S24
  • Samsung Galaxy S24 Ultra
  • Samsung Galaxy S24+
  • Samsung Galaxy S25
  • Samsung Galaxy S25 Ultra
  • Samsung Galaxy S25+
  • Samsung Galaxy Tab S8
  • Snapdragon 8 Elite Gen 5 QRD
  • Snapdragon X Elite CRD
  • Snapdragon X Plus 8-Core CRD
  • Snapdragon X2 Elite CRD
  • Xiaomi 12
  • Xiaomi 12 Pro
  • XR2 Gen 2 (Proxy)

Supported Chipsets

  • Qualcomm® QCS8275 (Proxy)
  • Qualcomm® QCS8550 (Proxy)
  • Qualcomm® SA7255P
  • Qualcomm® SA8295P
  • Qualcomm® SA8775P
  • Snapdragon® 8 Elite Mobile
  • Snapdragon® 8 Elite Gen 5 Mobile
  • Snapdragon® 8 Gen 1 Mobile
  • Snapdragon® 8 Gen 2 Mobile
  • Snapdragon® 8 Gen 3 Mobile
  • Snapdragon® 888 Mobile
  • Snapdragon® X Elite
  • Snapdragon® X Plus 8-Core
  • Snapdragon® X2 Elite

Related Models

See all models
View details for the Unet-Segmentation model.

Unet-Segmentation

Real-time segmentation optimized for mobile and edge.

View details for the FastSam-X model.

FastSam-X

Generate high quality segmentation mask on device.

View details for the MediaPipe-Selfie-Segmentation model.

MediaPipe-Selfie-Segmentation

Segments the person from background in a selfie image and realtime background segmentation in video conferencing.

View details for the YOLOv8-Segmentation model.

YOLOv8-Segmentation

Real-time object segmentation optimized for mobile and edge by Ultralytics.

View details for the DDRNet23-Slim model.

DDRNet23-Slim

Segment images or video by class in real-time on device.

Looking for more? See models created by industry leaders.

Discover Model Makers