Answer-first summary for fast verification
Answer: The model is overfitting in low-traffic areas, capturing noise as if it were a pattern, and underfitting in high-traffic areas, failing to capture the complexity of congested scenarios., The training dataset was disproportionately composed of images from congested areas, leading to a bias that affects model performance in less congested scenarios.
The decline in the AUC metric in high-traffic conditions suggests the model fails to generalize well across different traffic densities. Overfitting in low-traffic areas means the model learns noise as if it were a significant pattern, while underfitting in high-traffic areas indicates it cannot capture the complexity of these scenarios. Additionally, a training dataset biased towards congested areas could exacerbate the model's inability to perform well in less congested scenarios, making both A and C plausible explanations. However, the primary issue is the model's overfitting and underfitting, making A the most accurate answer, with C as a contributing factor.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
A self-driving car company deployed an image segmentation model to enhance its vehicle's navigation system. Post-deployment, the AUC metric showed a significant decline. Further analysis revealed that the model's performance was satisfactory in low-traffic scenarios but deteriorated in high-traffic conditions. Considering the need for the model to perform reliably across varying traffic densities to ensure passenger safety and compliance with regulatory standards, what is the most plausible explanation for this outcome? Choose the best option.
A
The model is overfitting in low-traffic areas, capturing noise as if it were a pattern, and underfitting in high-traffic areas, failing to capture the complexity of congested scenarios.
B
The AUC metric is inherently unsuitable for evaluating the performance of image segmentation models, regardless of the application context.
C
The training dataset was disproportionately composed of images from congested areas, leading to a bias that affects model performance in less congested scenarios.
D
The model suffers from the vanishing gradient problem, where gradients become too small during backpropagation, significantly hindering learning in layers close to the input.
E
Both A and C are correct, indicating that the model's issues stem from overfitting in low-traffic conditions and a biased training dataset favoring congested scenarios.