CS7643 Quiz 2 Exam 2025 | Certified Questions with 100%
Verified Answers | Guaranteed Excellent Scores - JUST
RELEASED, 100 % Verified
Convolution Features
Ans: edges
colors
textures
motifs (corners, shapes)
Receptive field
Ans: A region of an image (image patch) from which the node receives input. Usually denoted by a K1 x
K2 matrix.
Convolution vs Cross-correlation
Ans: Convolution: 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
, Ans: 1./ 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
Ans: The 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
Ans: (K1 x K2 + 1) x M
where M is the number of features
Relationship between convolution and cross-correlation
Ans: Duality: 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
Ans: When the kernel is fully on the image. (No padding)
Output size of the vanilla convolution,
given H, W, K1, K2
Verified Answers | Guaranteed Excellent Scores - JUST
RELEASED, 100 % Verified
Convolution Features
Ans: edges
colors
textures
motifs (corners, shapes)
Receptive field
Ans: A region of an image (image patch) from which the node receives input. Usually denoted by a K1 x
K2 matrix.
Convolution vs Cross-correlation
Ans: Convolution: 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
, Ans: 1./ 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
Ans: The 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
Ans: (K1 x K2 + 1) x M
where M is the number of features
Relationship between convolution and cross-correlation
Ans: Duality: 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
Ans: When the kernel is fully on the image. (No padding)
Output size of the vanilla convolution,
given H, W, K1, K2
