Question 22
Box A: top-left (2,2), bottom-right (10,12) Box B: top-left (6,5), bottom-right (14,15) Compute IoU rounded to 3 decimals.
Question 22: Box A: top-left (2,2), bottom-right (10,12) Box B: top-l…
Show answer
Correct answer: 0.212 (accepted within ±0.001)
Video solution
The video solution to this question is being recorded and will play here. Until then, the answer key is above.
Question 22 of 23 in 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 (Deep Learning For Computer Vision 07 Apr 26). It carries 1 mark.
This question was also asked in
More questions from this paper
- Why do very deep plain CNNs (without skip connections) sometimes show higher training error than shallower CNNs?
- In a standard ResNet-50 bottleneck block, the three convolutions are typically:
- In Inception/GoogLeNet modules, the main purpose of 1×1 convolutions is to:
- MobileNetV1 reduces computation primarily by using:
- EfficientNet’s key scaling idea is:
- You have a pretrained CNN backbone and only 500 labeled images for a new task. A strong first baseline is:
- When fine-tuning a model, what is a common way to prevent the new training from "overwriting" or destroying the useful …
- Which method produces a heatmap by weighting convolutional feature maps using gradients of a target class score?
- Which detector is a classic two-stage detector with an RPN + ROI feature extraction?
- Which statement is most accurate?
- RetinaNet is notable primarily because it introduced:
- A model that predicts a class label for every pixel without separating object instances is:
- Vanishing gradients in vanilla RNNs are largely caused by:
- Which statement is true?
- Which statements can be true in practice when fine-tuning with small batch sizes?
- Which statements are true?
- Which statements are true ?
- Input feature map: 14×14×128, output: 14×14×256, kernel: 3×3, stride 1, same padding, ignore bias. Compute number of pa…
- Using the same setup (Input feature map: 14×14×128, output: 14×14×256, kernel: 3×3, stride 1, same padding, ignore bias…
- A ResNet bottleneck block takes 256 channels in and uses: 1×1 conv to 256 channels → 3×3 conv at 256 → 1×1 conv to 1024…
- A detector uses three pyramid levels: P3 = 80×80, P4 = 40×40, P5 = 20×20. At each location, it uses 9 anchors (3 scales…
- Let query q = [1,2]T and keys: k1 = [1,0]T, k2 = [0,1]T, k3 = [1,1]T. Scores si = qT ki. Use softmax over scores. Use e…