Deep Learning For Computer Vision Week 6 Nptel Answers
Are you looking for the Deep Learning For Computer Vision Week 6 Nptel Answers (July-Dec)? You’ve come to the right place! Access the latest Deep Learning For Computer Vision Week 5 Nptel Answers
Deep Learning For Computer Vision Week 6 Nptel Answers
Deep Learning For Computer Vision Week 6 Nptel Answers (July-Dec 2024)
1. Match the following:
a) 1→v, 2→i, 3→iv, 4→ii
b) 1→iv, 2→i, 3→iii, 4→ii
c) 1→v, 2→iii, 3→i, 4→ii
d)1→v, 2→iii, 3→iv, 4→ii
Answer: d)1→v, 2→iii, 3→iv, 4→ii
2. Match the following:
a) 1→iv, 2→ii, 3→v, 4→i
b) 1→iv, 2→iii, 3→v, 4→ii
c) 1→iv, 2→v, 3→ii, 4→iii
d) 1→iii, 2→v, 3→i, 4→ii
Answer: d) 1→iii, 2→v, 3→i, 4→ii
3. Which of the following statements regarding the architectural design of ConvNEXT is incorrect? a) ConvNEXT employs depthwise convolutions followed by pointwise convolutions, similar to the MobileNet architecture, but with additional layer normalization and GELU activation. b) ConvNEXT replaces the traditional ResNet bottleneck block with a modified block that removes the ReLU activation function in favor of more non-linear operations like Swish. c) The ConvNEXT model increases the size of the convolutional kernels to 7×7 to better capture long-range dependencies, mimicking the self-attention mechanism in transformers. d) ConvNEXT introduces LayerNorm after the depthwise convolution and before the pointwise convolution to stabilize the training dynamics.
Answer: b) ConvNEXT replaces the traditional ResNet bottleneck block with a modified block that removes the ReLU activation function in favor of more non-linear operations like Swish.
4.Calculate the Average Precision (AP) for this class using the 11-point interpolation method, which averages the precision values at recall levels {0.0, 0.1, 0.2, …, 1.0}. The precision at recall 0.0 can be assumed to be 1.0. Based on these AP values, what is the mean Average Precision (mAP) across all three classes? a) 0.70 b) 0.69 c) 0.73 d) 0.76
5. Match the following computer vision tasks to situations:
a) 1 →iv, 2 →iii, 3 →ii, 4 →i
b) 1 →ii, 2 →iii, 3 →i, 4 →iv
c) 1 →iv, 2 →iii, 3 →i, 4 →ii
d) 1 →ii, 2 →iv, 3 →iii, 4 →i
Answer: b) 1 →ii, 2 →iii, 3 →i, 4 →iv
These are Deep Learning For Computer Vision Week 6 Nptel Answers
6. Which one of the following statements is false? a)nEfficientNet employs a compound scaling method to improve model efficiency and accuracy across different scales. b) MobileNet utilizes depthwise separable convolutions to reduce the computational complexity of the network. c)DenseNet only connects each layer to the last layer in a feedforward fashion to address the vanishing gradient problem. d)SeNet incorporates spatial squeeze-and-excitation blocks to enhance the representation power of the network by explicitly modeling channel-wise dependencies.
Answer: c)DenseNet only connects each layer to the last layer in a feedforward fashion to address the vanishing gradient problem.
7. Which one of the following object detection networks uses an ROI pooling layer? a)Fast R-CNN b)R-CNN c)YOLO d)All of the above
Answer: a)Fast R-CNN
8.Consider two 12×12 bounding boxes (one on the upper left and one on the lower right) in an image with an overlapping region of 8 × 8. The Intersection over Union (IoU) score between the two boxes is (choose the closest value): a) 10% b) 18% c) 28% d) 35%
Answer: c) 28%
These are Deep Learning For Computer Vision Week 6 Nptel Answers
All Weeks Answers of Deep Learning for Computer Vision: Click here
