30 Questions
What is the definition of similarity used to compare two boxes?
Intersection over Union (IoU)
What is the primary condition for a prediction P to be considered a true positive?
P and G have the same category label
What IoU value is considered 'almost perfect'?
IoU > 0.9
What is the class score of 'cat' in the given model?
0.9
What is the purpose of ranking by score in defining matches?
To break ties between multiple predictions
What is a prediction P matched to if it satisfies conditions (1-3)?
A ground truth G
What is the input size of the fully connected layer?
4096 to 1000
What type of problem is localization treated as in this model?
Regression
What strategy is rarely used in practice to define matches?
Optimal bipartite matching
What is the shape of the correct box in this model?
(x', y', w', h')
What is the loss function composed of in this model?
Lcls + Lreg
What is the purpose of the softmax function in this model?
To calculate the class scores
What is the most popular metric used in evaluation?
Average precision
What is the purpose of having multiple definitions of AP?
To accommodate different dataset requirements
Why did early datasets use an IoU threshold of 0.5?
Because the detection problem was too hard
What is the goal of achieving an AP of 1?
To achieve perfect recall and precision
Why are larger datasets extending to multiple IoU thresholds?
Because the detection problem is established and there's good progress
What is the significance of AP being a generic metric?
Doing well on AP should be good for many applications
What is the main motivation behind defining Average Precision (AP)?
To have a single number that communicates the model's performance on the dataset
What does Precision@s measure?
The fraction of detections that are correct with score >= s
What is the purpose of the Precision-Recall curve?
To visualize the trade-off between precision and recall
What is the range of Average Precision (AP)?
0 to 1
What is Recall@s measuring?
The fraction of ground-truth objects detected with score >= s
How is Average Precision (AP) calculated?
The area under the Precision-Recall curve
What is AP[ℂ] an abbreviation for?
Average Precision of multiple categories
What is AP[C, IoU] an abbreviation for?
Average Precision of Category C with IoU threshold
What does mAP represent?
Mean Average Precision
What does AP of 1 represent?
Perfect precision and perfect recall
What is 𝕋 in the context of AP?
A set of IoU thresholds
What is the extended formula for AP?
!(∑AP[C, 𝕋]) / |ℂ|
This quiz tests your understanding of object detection and classification concepts, including class scores, correct labels, and loss functions. It also covers fully connected layers and vector dimensions.
Make Your Own Quizzes and Flashcards
Convert your notes into interactive study material.
Get started for free