Max pooling vs average pooling — when do you pick each?
easyAnswer
- Max pool: keeps the strongest activation in the window — sharper features, invariance to small translations, dominant in classification CNNs.
- Average pool: smoother, retains overall energy — better in generative / decoder paths where you don't want to lose detail.
- Modern architectures often replace pool with strided convs (learnable downsampling).
- Global average pool (GAP) at the end of a CNN replaces the fully-connected head and reduces overfitting.
Check yourself — multiple choice
- Only max pool is useful
- Max keeps the strongest activation (sharp features); avg smooths (retains energy); GAP replaces FC heads
- Avg pool always wins
- They differ only in memory
Max = sharp features / translation invariance; Avg = smooth energy retention.
#cnn
Practise Deep Learning
214 interview questions in this topic.
Related questions
- What inductive biases do CNNs have?
- What is the receptive field in a CNN?
- Compute the output shape of a 2D convolution with input (H, W), kernel k, stride s, padding p, dilation d.
- SAME vs VALID vs REFLECT padding — what are the practical differences?
- What is a dilated (atrous) convolution?
- What is a transposed convolution ('deconv') and its checkerboard artifact issue?