CS7643-QUIZ2 EXAM WITH CORRECT
QUESTIONS AND ANSWERS 2025
Convolution Features - CORRECT-ANSWERSedges
colors
textures
motifs (corners, shapes)
Receptive field - CORRECT-ANSWERSA region of an image (image patch) from which
the node receives input. Usually denoted by a K1 x K2 matrix.
Convolution vs Cross-correlation - CORRECT-ANSWERSConvolution: flip the kernel
(rotate 180) and take the dot product with image patch
Cross-correlation: do not flip the kernel to take the dot product with image patch
,Advantage of using image patch - CORRECT-ANSWERS1./ Reduces the input
parameters to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing - CORRECT-ANSWERSThe weights will represent what types of features
we will extract. The weights (W) will be the same for each output node with respect to a
specific kernel, regardless of the specific image patch we are looking at.
The total number of input parameters:
K1 x K2 + 1
Input parameters with multiple feature extractions - CORRECT-ANSWERS(K1 x K2 + 1) x
M
where M is the number of features
, Relationship between convolution and cross-correlation - CORRECT-ANSWERSDuality: If
cross-correlation is the forward pass (which is the easier operation), the convolution
operation is going to be the backward pass to calculate gradients (vice versa)
Valid convolution - CORRECT-ANSWERSWhen the kernel is fully on the image. (No
padding)
Output size of the vanilla convolution,
given H, W, K1, K2 - CORRECT-ANSWERS(H - K1 + 1) x (W - K2 + 1)
How to add padding - CORRECT-ANSWERSIncreases the size of the image with P in
both directions (top & bottom, left & right)
--> (H + 2P) x (W + 2P)
Can be filled with zeros or mirror the image
QUESTIONS AND ANSWERS 2025
Convolution Features - CORRECT-ANSWERSedges
colors
textures
motifs (corners, shapes)
Receptive field - CORRECT-ANSWERSA region of an image (image patch) from which
the node receives input. Usually denoted by a K1 x K2 matrix.
Convolution vs Cross-correlation - CORRECT-ANSWERSConvolution: flip the kernel
(rotate 180) and take the dot product with image patch
Cross-correlation: do not flip the kernel to take the dot product with image patch
,Advantage of using image patch - CORRECT-ANSWERS1./ Reduces the input
parameters to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing - CORRECT-ANSWERSThe weights will represent what types of features
we will extract. The weights (W) will be the same for each output node with respect to a
specific kernel, regardless of the specific image patch we are looking at.
The total number of input parameters:
K1 x K2 + 1
Input parameters with multiple feature extractions - CORRECT-ANSWERS(K1 x K2 + 1) x
M
where M is the number of features
, Relationship between convolution and cross-correlation - CORRECT-ANSWERSDuality: If
cross-correlation is the forward pass (which is the easier operation), the convolution
operation is going to be the backward pass to calculate gradients (vice versa)
Valid convolution - CORRECT-ANSWERSWhen the kernel is fully on the image. (No
padding)
Output size of the vanilla convolution,
given H, W, K1, K2 - CORRECT-ANSWERS(H - K1 + 1) x (W - K2 + 1)
How to add padding - CORRECT-ANSWERSIncreases the size of the image with P in
both directions (top & bottom, left & right)
--> (H + 2P) x (W + 2P)
Can be filled with zeros or mirror the image
