Question 22
Continual learning
Zero-shot learning
Few-shot learning
Unsupervised learning
Deep Learning for Computer Vision End Term 28 Apr 2024 — Question 22
Show answer
Correct answer
Few-shot learning
Question 22 of 44 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) End Term paper sat on 28 Apr 2024, in the January 2024 term (IIT M DEGREE AN EXAM QDB3 28 Apr 2024). It carries 2 marks.
More questions from this paper
- Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these…
- What is the role of the Gaussian blur in the Canny edge detection algorithm, and how does the choice of the standard de…
- Which property of the SIFT descriptor is primarily responsible for its resilience to changes in scale, viewpoint, and i…
- In the Maximally Stable External Regions (MSER) algorithm, how does the tree structure contribute to the efficiency of …
- In which scenarios is the Random Sample Consensus (RANSAC) algorithm more suitable compared to least squares?
- In what way does VLAD (Vector of Locally Aggregated Descriptors) differ from Bag of Words (BoW) in representing visual …
- How does pyramid matching differ from Speeded-Up Robust Features (SURF) in image matching?
- In the context of Convolutional Neural Networks (CNNs), what is the primary challenge associated with backpropagation c…
- What is the primary advantage of Depthwise Separable Convolutions compared to standard Convolutional Neural Network (CN…
- Which of the following strategies can help mitigate the risk of overfitting when fine-tuning pretrained models on a sma…
- What is the primary advantage of visualizing patches of maximally activating neurons in neural network interpretation?
- Which layer of the neural network does Grad-CAM typically operate on?
- Which component of Grad-CAM is responsible for weighting the importance of each feature map?
- What is the primary role of the Gram matrix in neural style transfer?
- What is a potential limitation of non-maximum suppression (NMS) algorithms in object detection?
- What is a key feature of focal loss that distinguishes it from traditional loss functions in object detection?
- What is a unique challenge faced by Siamese networks in comparison to traditional neural networks?
- Consider the following assertion and reason, and state which of them is true.\ Assertion: ProgressiveGAN uses Minibatch…
- Figure question
- Which of the following statements is false?
- Match the following: | 1)VAE | i) z = \mu + \sigma \odot \epsilon;\ \epsilon \sim \mathcal{N}(0, 1) | |---|---| | 2)GAN…
- Figure question
- What is the advantage of the progressive training methodology proposed in the Progressive GAN paper?
- Contrastive Language Image Pre-training (CLIP) Can be used as a zero-shot classifier.
- Figure question
- The cornerness score of the center pixel for the image represented by the matrix below is . | 1 | 0 | 0 | 0 | 1 | |---|…
- Consider a 3 \times 3 grayscale image in terms of pixel intensities as shown in matrix form below. | 9 | 1 | 6 | |---|-…
- Figure question
- Consider a Faster R-CNN object detection framework, which is being trained with a mini-batch size of 2. The RPN produce…
- Transformer encoder requires a sequence of as input.
- Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these…
- Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these…
- Given word embeddings for two words and weight matrix to generate queries, keys and values as below (in practice, these…
- NOTE: Enter your answer in two decimal places.
- NOTE: Enter your answer in two decimal places.
- NOTE: Enter your answer in two decimal places.
- Based on the above data, answer the given subquestions.
- Based on the above data, answer the given subquestions.
- Based on the above data, answer the given subquestions.
- Enter the correct answer for blank(a):
- Enter the correct answer for blank(b):
- Enter the correct answer for blank(a):
- Enter the correct answer for blank(b):