Deep Learning for Computer Vision · Quiz 2 · Jan 2024

TRUE

FALSE       **DL(CV)** **Section Id :** 64065353063 **Section Number :** 10 **Section type :** Online **Mandatory or Optional :** Mandatory **Number of Questions :** 23 **Number of Questions to be attempted :** 23 **Section Marks :** 50 **Display Number Panel :** Yes **Section Negative Marks :** 0 **Group All Questions :** No **Enable Mark as Answered Mark for Review and** Yes **Clear Response :** **Maximum Instruction Time :** 0

Tanh activation function can be represented as below in terms of sigmoid activation function: tanh(x) = 2σ(2x) − 1, where σ = sigmoid activation function

The derivative of the Sigmoid activation function is symmetric around the origin.

Gradient of sigmoid neuron at saturation explodes

sigmoid activation is centered around 0.5 whereas tanh activation is centered around 0.

Grad-CAM saliency map only computes gradients for important pixels while calculating weights, so pixels that contribute more to a specific class are considered

Grad-CAM can’t generate explanation directly from the given CNN and needs additional retraining

Grad-CAM is very reliable at identifying multiple instances of objects with occlusions

Grad-CAM can help localize objects without positional supervision

Activation maximization methods identify input image region that maximally activates specific neurons in the network.

Filter visualization techniques display the learned weights of convolutional filters in the network.

Kernel visualization involves directly observing the values of convolutional filters during network training.

Principal Component Analysis (PCA) is commonly employed to reduce the dimensionality of feature maps for visualization purposes.

Soft Attention is smooth and differentiable

Variance reduction techniques are used to train Hard Attention models

Soft Attention is computationally cheaper than Hard Attention when the source input is large

The inference (test time) overhead is low in Hard Attention when compared to Soft Attention models

May not capture all features

Needs small sample size

Slow to run

None of these

p(x)

p(x|y)

p(y|x)

p(x, y)

1→ vi, 2→ iii, 3→ v, 4 → i

1→ i, 2→ iv, 3 → iii, 4→ ii

1→ i, 2→ v, 3 → iii, 4→ iv

1→ iv, 2→ iii, 3→ ii, 4 → i

Feature Concatenation

Dimension Reduction

Gradient-weighted Class Activation Mapping (Grad-CAM)

Random Initialization

1→ iv, 2→ iii, 3→ ii, 4 → i

1→ ii, 2→ iii, 3 → i, 4 →iv

1→ iv, 2→ iii, 3→ i, 4 → ii

1→ ii, 2→ iv, 3 → iii, 4→ i

21%

25%

33%

37%

The goal of triplet loss is to ensure that the distance between the anchor and the negative sample is at least ’margin’ less than the distance between anchor and positive sample.

Face identification is a multi-class classification problem whereas face verification is a binary classification problem

Both the goal of triplet loss is to ensure that the distance between the anchor and the negative sample is at least ’margin’ less than the distance between anchor and positive sample & Face identification is a multi-class classification problem whereas face verification is a binary classification problem

None of these

Object detection

Image segmentation

Texture analysis

Image denoising

Sigmoid of alignment scores

Softmax of alignment scores

ReLU of alignment scores

None of these

Encoder

Decoder

Positional Encoding

Recurrent Connections

Both assertion and reason are true, and the reason is the correct explanation of assertion

Both assertion and reason are true, but the reason is not the correct explanation of assertion

Assertion is true, the reason is false

Both assertion and reason are false

1→ iii, 2→ ii, 3 → vi, 4→ i

1→ v, 2→i, 3 → vi, 4→ iii

1→ ii, 2→ i, 3 → ii, 4 → iii

1→ i, 2 →ii, 3 → vi, 4→ iv