Instance Segmentation MCQ 15 Questions
Time: ~25 mins Advanced

Instance Segmentation MCQ

Separate objects of the same class with distinct masks; two-stage Mask R-CNN style heads and alignment tricks.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Mask

Per object

Box

Proposal

ROIAlign

No quantize

AP_mask

IoU

Instance segmentation

Each object instance gets its own mask—even if two people share the class “person.” Often built on top of strong object detectors with a parallel mask branch.

Mask R-CNN

Faster R-CNN backbone + FPN + class/box head + small FCN per ROI to predict a fixed-resolution binary mask.

Details

ROIAlign

Bilinear sampling without harsh quantization—fixes misalignment vs ROI pooling for masks.

AP_mask

Average precision over mask IoU thresholds—COCO-style reporting.

vs semantic

Semantic merges same-class instances; instance keeps them separate.

Alternatives

One-stage instance (YOLACT), query-based (Mask2Former)—tradeoffs in speed vs accuracy.

Output

N instances: class, box, binary mask per instance

Pro tip: Mask NMS / soft masks matter when instances overlap heavily.