Zubnet AILearnWiki › Pooling
Fundamentals

Pooling

Max Pooling, Average Pooling
An operation that reduces the spatial dimensions of data by summarizing a region into a single value. Max pooling takes the maximum value in each region. Average pooling takes the mean. In CNNs, pooling layers downsample feature maps between convolutional layers. In Transformers, pooling combines token representations into a single vector (e.g., for classification).

Why it matters

Pooling is how neural networks go from local features to global understanding. A CNN might start with 224×224 feature maps and pool down to 7×7 by the final layer, progressively summarizing spatial information. In NLP, mean pooling over token embeddings is the standard way to create a single sentence embedding from a sequence of token representations.

Deep Dive

In CNNs: a 2×2 max pool with stride 2 takes every 2×2 region, keeps the maximum value, and reduces each spatial dimension by half. This achieves two things: translation invariance (small shifts in the input don't change the output) and dimensionality reduction (fewer values to process in subsequent layers). Average pooling does the same but takes the mean, which preserves more information but is less robust to noise.

Pooling in NLP

To create a fixed-size embedding from a variable-length sequence of tokens, you need to pool. Common strategies: [CLS] token pooling (use the representation of a special token, as in BERT), mean pooling (average all token representations — usually the best for sentence embeddings), max pooling (take the element-wise max across tokens), and weighted pooling (weight tokens by attention scores). Most embedding models use mean pooling for its simplicity and effectiveness.

Global Average Pooling

In modern vision architectures, global average pooling replaces the fully connected layers that older CNNs used for classification. Instead of flattening the final feature map into a vector (which creates millions of parameters), global average pooling averages each feature map channel to a single number. This produces a compact representation with no learned parameters, acting as a strong regularizer. Vision Transformers use a similar approach with the [CLS] token.

Related Concepts

← All Terms
← PixVerse Positional Encoding →