Architecture Fundamentals Flashcards

Which pooling operation is most commonly used in CNNs and what does it compute?

Answer: Max pooling — selects the maximum value in the pooling window

Max pooling takes the largest activation within each region, retaining the strongest feature response and providing a degree of translation invariance.

In DenseNet, how does each layer receive its input?

Answer: From all preceding layers via concatenation

DenseNet concatenates feature maps from all preceding layers as input to each layer, maximizing feature reuse and enabling gradient flow through the entire network.

What is the key innovation in MobileNetV2's inverted residual block compared to standard residual blocks?

Answer: It expands channels before the depthwise convolution, then compresses with a linear bottleneck

MobileNetV2 inverts the bottleneck by expanding channels first, applying depthwise conv, then projecting back to a low-dimensional space with a linear activation.

What does 'dilation' (atrous convolution) add to a standard convolution?

Answer: Spaces between filter elements, enlarging the receptive field without increasing parameters

Dilated convolution inserts gaps (holes) between filter weights, exponentially growing the receptive field while keeping the parameter count and resolution constant.

In a fully convolutional network (FCN), what replaces the fully connected layers to enable pixel-wise predictions?

Answer: Transposed convolutions (or bilinear upsampling) to recover spatial resolution

FCNs replace dense layers with convolutional ones and use transposed convolutions to upsample feature maps back to the input resolution for dense prediction.

What is the purpose of the squeeze-and-excitation (SE) block in SENet?

Answer: To recalibrate channel-wise feature responses by modeling inter-channel dependencies

The SE block globally pools feature maps, learns channel importance weights via two FC layers, and scales channels accordingly — acting as channel-wise attention.

How does a transposed convolution (sometimes called deconvolution) differ from a standard convolution in terms of spatial output?

Answer: It increases spatial dimensions, making it useful for upsampling

Transposed convolution is the gradient operation of a forward convolution; it increases spatial size and is used in decoders, GANs, and segmentation networks.