Neural Network Convolutional Neural Networks 3

Question 1

What is the primary challenge that fully convolutional networks (FCNs) address?

Accepted Answer

Dense pixel-wise prediction tasks like semantic segmentation

Answer

FCNs replace fully connected layers with convolutional layers, enabling dense pixel-wise output for tasks like semantic segmentation where each pixel needs a class label.

Question 2

What is dilated (atrous) convolution and what problem does it solve?

Accepted Answer

A convolution with gaps in the filter to expand receptive field without extra parameters or pooling

Answer

Dilated convolution inserts gaps (dilation rate) between filter elements, exponentially expanding the receptive field without increasing parameters or reducing spatial resolution.

Question 3

How does instance normalization differ from batch normalization?

Accepted Answer

Instance normalization normalizes per-sample per-channel; batch normalization normalizes across the batch dimension

Answer

Instance normalization computes statistics per sample per channel (ignoring batch), while batch normalization computes statistics across the entire batch per channel.

Question 4

What is non-maximum suppression (NMS) used for in object detection CNNs?

Accepted Answer

Eliminating redundant overlapping bounding box predictions to retain the most confident detections

Answer

NMS removes duplicate overlapping bounding boxes by retaining only the box with the highest confidence score among boxes with high IoU overlap.

Question 5

What metric is used to measure the overlap between predicted and ground-truth bounding boxes in object detection?

Accepted Answer

Intersection over Union (IoU)

Answer

Intersection over Union (IoU) measures the ratio of the overlapping area to the combined area of predicted and ground-truth boxes, ranging from 0 (no overlap) to 1 (perfect match).

Neural Network Practice Test

Neural Network Practice Test

Neural Network Convolutional Neural Networks 3