---
id: wiki-2026-0508-pooling
title: Pooling
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [Max Pooling, Average Pooling, Global Pooling]
duplicate_of: none
source_trust_level: A
confidence_score: 0.9
verification_status: applied
tags: [deep-learning, cnn, pooling, downsampling]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: python
  framework: pytorch
---

# Pooling

## 매 한 줄
> **"매 spatial/sequence dimension downsample — invariance + receptive field 확대."**. CNN 시대의 staple (max/avg pool), 매 modern Transformer는 거의 안 씀 (strided conv 또는 attention pooling). Global pool은 여전히 classification head 표준.

## 매 핵심

### 매 종류
- **Max Pooling**: window 내 max — translation invariance, edge-preserve.
- **Average Pooling**: window 평균 — smooth, all-pixel contribute.
- **Global Average Pooling (GAP)**: 매 entire feature map → 단일 값. ResNet/EfficientNet head.
- **Adaptive Pooling**: output size fix → input size 무관 (PyTorch `AdaptiveAvgPool2d`).
- **Attention Pooling**: weighted sum, learned weights — ViT [CLS] 또는 perceiver.
- **L_p Pooling, Stochastic Pooling, Mixed Pooling**: less common, occasionally robust.

### 매 왜 사용
- **Downsampling**: spatial size 줄여 compute / params 감소.
- **Invariance**: small translation에 robust.
- **Receptive field 확대**: deeper layer가 wider context 봄.
- **Overfitting 방지**: parameter-free regularization 효과.

### 매 modern shift
- 2020+ Transformer 시대 — 매 pool 자리에 strided conv (stage transition) 또는 patch merging (Swin) 또는 attention pooling.
- ConvNeXt도 strided conv 사용.
- GAP은 classification head에서 여전히 universal.

## 💻 패턴

### Max / Avg pool 기본
```python
import torch.nn as nn
maxp = nn.MaxPool2d(kernel_size=2, stride=2)   # H,W /2
avgp = nn.AvgPool2d(kernel_size=2, stride=2)
```

### Global Average Pooling (classification head)
```python
import torch.nn as nn
class Head(nn.Module):
    def __init__(self, c, n_cls):
        super().__init__()
        self.gap = nn.AdaptiveAvgPool2d(1)
        self.fc  = nn.Linear(c, n_cls)
    def forward(self, x):           # x: (B, C, H, W)
        x = self.gap(x).flatten(1)  # (B, C)
        return self.fc(x)
```

### Adaptive pool (variable input size)
```python
import torch, torch.nn as nn
pool = nn.AdaptiveAvgPool2d((7, 7))  # 항상 7x7 output
x = torch.randn(2, 64, 33, 41)       # 임의 spatial
y = pool(x)  # (2, 64, 7, 7)
```

### Attention Pooling (ViT [CLS])
```python
import torch, torch.nn as nn
class AttnPool(nn.Module):
    def __init__(self, d, heads=8):
        super().__init__()
        self.q = nn.Parameter(torch.randn(1, 1, d))
        self.attn = nn.MultiheadAttention(d, heads, batch_first=True)
    def forward(self, x):  # x: (B, N, D)
        B = x.size(0)
        q = self.q.expand(B, -1, -1)
        out, _ = self.attn(q, x, x)
        return out.squeeze(1)  # (B, D)
```

### Patch Merging (Swin Transformer)
```python
import torch, torch.nn as nn
class PatchMerging(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.norm = nn.LayerNorm(4*dim)
        self.reduction = nn.Linear(4*dim, 2*dim, bias=False)
    def forward(self, x):  # x: (B, H, W, C)
        x0 = x[:, 0::2, 0::2, :]; x1 = x[:, 1::2, 0::2, :]
        x2 = x[:, 0::2, 1::2, :]; x3 = x[:, 1::2, 1::2, :]
        x = torch.cat([x0,x1,x2,x3], -1)
        return self.reduction(self.norm(x))
```

### 1D pool (sequence / audio)
```python
import torch.nn as nn
pool1d = nn.MaxPool1d(kernel_size=4, stride=4)  # (B, C, T) -> (B, C, T/4)
gap1d  = nn.AdaptiveAvgPool1d(1)
```

### Set/Graph pooling (mean/max/sum)
```python
import torch
def set_mean(x, mask):  # x:(B,N,D), mask:(B,N)
    m = mask.unsqueeze(-1).float()
    return (x*m).sum(1) / m.sum(1).clamp(min=1)
```

## 매 결정 기준
| 상황 | Approach |
|---|---|
| Classification final feature | Global Avg Pooling |
| Variable input image | AdaptiveAvgPool2d |
| Edge-preserve detection | Max Pool 또는 strided conv |
| Transformer stage transition | Patch merging / strided conv |
| Set/sequence aggregation | Attention pool |
| Audio waveform | 1D max/avg pool 또는 strided conv |

**기본값**: feature map → GAP, downsample → strided conv (modern).

## 🔗 Graph
- 부모: [[Deep_Learning]]
- 변형: [[Max_Pooling]] · [[Average_Pooling]]
- 응용: [[Image-Classification-Mastery]] · [[ResNet]] · [[ViT]]

## 🤖 LLM 활용
**언제**: CNN backbone에서 spatial reduce, classification head GAP, set/graph aggregation.
**언제 X**: dense prediction (segmentation, detection)에서 매 정보 손실 — skip connection 결합 또는 dilated conv 고려.

## ❌ 안티패턴
- **Pool then upsample for segmentation without skip**: 매 detail 손실. U-Net skip 사용.
- **MaxPool everywhere in modern arch**: 매 strided conv가 매 학습 가능 — 거의 dominant.
- **Flatten without GAP**: classification head fully-connected로 들어가면 매 huge params + overfit.
- **Pool over tokens with [CLS] available**: attention pool 또는 [CLS] readout 매 better.

## 🧪 검증 / 중복
- Verified (PyTorch docs nn.MaxPool2d, AdaptiveAvgPool, Swin Transformer paper, ConvNeXt paper).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — pooling types + modern shift to strided conv / attention pool |