Depthwise Separable Convolution

Depthwise Separable Convolution: Depthwise separable convolution factorizes a standard convolution into spatial filtering per channel followed by channel mixing. It is a common building block in efficient convolutional networks. The depthwise stage applies one k × k filter independently to each input channel.

In italiano: Depthwise Separable ConvolutionLegge III · Come una rete impara dai dati

The depthwise stage applies one k × k filter independently to each input channel. The pointwise stage then uses a 1 × 1 convolution to combine channels and set the output width. Separating these operations substantially reduces parameters and multiply-accumulate operations compared with a standard convolution.

Formula

Standard: k²CᵢₙCₒᵤₜ parameters; depthwise separable: k²Cᵢₙ + CᵢₙCₒᵤₜ

Numerical example

import torch.nn as nn

# 32 input channels, 64 output channels, 3x3 spatial filters
block = nn.Sequential(
    nn.Conv2d(32, 32, 3, padding=1, groups=32, bias=False),
    nn.Conv2d(32, 64, 1, bias=False)
)
# 3*3*32*64 = 18,432 standard parameters
# 3*3*32 + 32*64 = 2,336 factorized parameters

When to use it

Use it in mobile, edge and latency-sensitive vision models, including MobileNet-style architectures, when reducing compute and parameter count is a primary constraint.

Limitations

The factorization restricts how spatial and channel information interact and may reduce representational capacity. Actual latency also depends on hardware support, memory access and operator implementation, not only parameter count.

Examples

  • MobileNet architecture
  • Efficient CNNs
  • Mobile deployment

Autovalutazione

Tre domande per verificare la comprensione della voce. Le spiegazioni restano disponibili anche senza JavaScript.

1. Che cos’è Depthwise Separable Convolution?
Spiegazione

Depthwise Separable Convolution: Depthwise separable convolution factorizes a standard convolution into spatial filtering per channel followed by channel mixing. It is a common building block in efficient convolutional networks. The depthwise stage applies one k × k filter independently to each input channel.

2. Quale applicazione è coerente con Depthwise Separable Convolution?
Spiegazione

Use it in mobile, edge and latency-sensitive vision models, including MobileNet-style architectures, when reducing compute and parameter count is a primary constraint.

3. Quale voce è collegata a Depthwise Separable Convolution?
Spiegazione

Le voci correlate sono scelte per collegamento tecnico, non per somiglianza casuale.