Semantic Segmentation MCQ 15 Questions
Time: ~25 mins Advanced · Popular

Semantic Segmentation MCQ

Dense labeling: each pixel gets a class. Encoder–decoder architectures, multi-scale context, skip connections, and how metrics differ from detection.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Per-pixel

Class map

Encoder

Downsample

Decoder

Upsample

IoU

Overlap

Semantic segmentation

Every pixel is classified (sky, road, person, …) without separating object instances. Fully convolutional networks replaced sliding-window classifiers for dense outputs.

U-Net idea

Skip connections fuse fine spatial detail from the encoder with semantic features from the bottleneck—sharp boundaries.

Building blocks

FCN

Replace FC layers with 1×1 convs; upsample feature maps to input resolution.

ASPP / dilation

Multi-scale context without losing resolution too aggressively.

Loss

Per-pixel cross-entropy; class imbalance may need weighting or focal-style ideas.

vs instance

Semantic does not separate two people as different IDs—instance segmentation adds that.

Output

H×W label map (or H×W×C logits)

Pro tip: Report mIoU per class—mean hides failure on rare categories.