Deep Learning for Computer Vision End Term 13 Sept 2026 — Question 37
Show answer
Correct answer: 1.364 (accepted within ±0.001)
Question 37 of 37 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) End Term paper sat on 13 Sept 2026, in the May 2026 term (Deep Learning For Computer Vision 13 Sep 26). It carries 4 marks.
More questions from this paper
- An RGB image of size 128×96 is stored with 32-bit floating-point values for every channel. Ignoring metadata, how many …
- Let a 1-D filter be h=[2,-1,3]. A library routine performs cross-correlation. Which filter should be supplied to the ro…
- At a point on an ideal straight intensity edge, the local image-gradient vector is most naturally interpreted as pointi…
- An image is smoothed successively with Gaussian kernels of standard deviations 2 and 3. Ignoring discretization, the eq…
- Which design choice is most directly responsible for the rotation robustness of a SIFT descriptor?
- A hidden activation h is used by two downstream branches, and both branches affect the same scalar loss L. During backp…
- Suppose successive gradients keep pointing in a similar direction over several updates. Compared with plain gradient de…
- Training loss continues to decrease, but validation loss has begun to increase consistently. Which interpretation is mo…
- A 3×3 convolution maps 16 input channels to 32 output channels. If the input spatial size changes from 64×64 to 128×128…
- A convolution kernel is reused at many spatial locations. The gradient of the loss with respect to one kernel coefficie…
- Figure question
- A depthwise-separable convolution first applies a spatial filter independently to each input channel and then uses a 1×…
- When adapting a pretrained CNN to a related task with a relatively small labeled dataset, which training choice is gene…
- Which processing pattern is characteristic of a two-stage object detector?
- For semantic image segmentation with C classes, the model output before the final class decision is naturally organized…
- Compared with a basic recurrent update, the gating mechanisms in LSTMs and GRUs are primarily intended to:
- In self-attention, changing the query vector for one token while keeping keys and values fixed directly changes:
- A standard way to convert an image for processing by a Vision Transformer is to:
- Which statement correctly distinguishes the two model families?
- Classifier-free guidance during sampling is based on combining:
- Select all correct statements
- Select all correct statements .
- Select all correct statements.
- Select all correct statements.
- Select all correct statements .
- Select all correct statements.
- Select all correct statements.
- Select all correct statements .
- An input feature map has spatial size 63×63. A 5×5 convolution is applied with stride 2 and padding 1. Compute the outp…
- An image is smoothed successively by Gaussian kernels with σ1=1.2 and σ2=1.6. Ignoring discretization, compute the equi…
- Figure question
- A convolutional layer uses 3×3 kernels, 16 input channels and 32 output channels. The layer has one bias per output cha…
- A depthwise-separable convolution receives 32 channels. It uses a 3×3 depthwise convolution followed by a 1×1 pointwise…
- Figure question
- Figure question
- Figure question