What is GroupNorm and when do you use it?
mediumAnswer
- Divide channels into G groups, normalize each group per example.
- No dependence on batch size — works with batch=1, useful for detection / segmentation where memory forces small batches, or for very high-resolution training.
- Middle ground between LayerNorm (all channels one group) and InstanceNorm (each channel its own group).
- Standard in Detectron2, MMDetection, and small-batch computer vision.
Check yourself — multiple choice
- GroupNorm depends on batch size
- Normalize channels in groups per example — batch-independent, great for small-batch CV
- GroupNorm requires batch > 128
- Same as LayerNorm
GroupNorm normalizes per group of channels per example — no batch dependence.
#normalization
Practise Deep Learning
214 interview questions in this topic.