Quiz Space

Deep Learning for Computer Vision Quiz 2: 12 April 2026 (January 2026 term)

Question 1

+1 markOne correct option

Why do very deep plain CNNs (without skip connections) sometimes show higher training error than shallower CNNs?

  1. A

    The increased capacity leads to severe overfitting on the training set before convergence can be reached.

  2. B

    Optimization becomes harder; skip connections make learning identity mappings easier and improve gradient flow.

  3. C

    The receptive field becomes excessively large, causing the network to lose fine-grained spatial information.

  4. D

    Saturated activations cause exploding gradients that cannot be mitigated by standard initialization techniques.

Question 2

+1 markOne correct option

In a standard ResNet-50 bottleneck block, the three convolutions are typically:

  1. A

    3×3, 1×1, 3×3

  2. B

    1×1, 3×3, 1×1

  3. C

    1×1, 5×5, 1×1

  4. D

    3×3, 3×3, 3×3

Question 3

+1 markOne correct option

In Inception/GoogLeNet modules, the main purpose of 1×1 convolutions is to:

  1. A

    Increase the receptive field of subsequent convolutional layers without downsampling.

  2. B

    Reduce channel dimensionality (bottleneck) and add non-linearity

  3. C

    Act as a differentiable substitute for max-pooling operations to preserve exact spatial hierarchies.

  4. D

    Project the feature maps into a higher-dimensional space to separate entangled features.

20 more questions in this paper

Sign in with Google — it is free — to see every question with its answer and explanation, practise it in learning mode, or take it as a timed mock test.

More on the Deep Learning for Computer Vision Quiz 2 12 Apr 2026 paper

The IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 2 paper sat on 12 Apr 2026, in the January 2026 term: 23 questions for 23 marks in 120 minutes. The first 3 questions are below. Sign in with Google — it is free — to see the whole paper with its answers and explanations, in learning mode or as a timed mock test.

FeatureDeep Learning for Computer Vision Quiz 2 12 Apr 2026 at a glance
TermJanuary 2026 term
SubjectDeep Learning for Computer Vision
Course codeBSDA5006
Questions23
Marks23
Duration120 min
MCQ14
MSQ3
Numerical6
Official paperDeep Learning For Computer Vision 07 Apr 26
Negative markingNo negative marking.
Updated

Same Quiz 2, other subjects

More Deep Learning for Computer Vision