ResNet and skip connections in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - ResNet and skip connections

Which metric matters for ResNet and skip connections and WHY

For ResNet models, common metrics like accuracy and loss are important to see how well the model learns. But because ResNet is deep, watch training and validation loss to check if skip connections help avoid problems like vanishing gradients. Skip connections help the model learn better by letting information flow directly, so metrics like training speed and stable accuracy gains matter.

Confusion matrix example for ResNet image classification

      | Predicted Cat | Predicted Dog |
      |---------------|---------------|
      | True Cat: 45  | False Dog: 5  |
      | False Cat: 3  | True Dog: 47  |

      Total samples = 45 + 5 + 3 + 47 = 100

      Precision (Cat) = TP / (TP + FP) = 45 / (45 + 3) = 0.9375
      Recall (Cat) = TP / (TP + FN) = 45 / (45 + 5) = 0.9

      Precision (Dog) = 47 / (47 + 5) = 0.904
      Recall (Dog) = 47 / (47 + 3) = 0.94
    

Precision vs Recall tradeoff with ResNet

Imagine ResNet is used to detect cats in photos. If you want to be sure every cat found is really a cat, you want high precision (few false cats). But if you want to find all cats, even if some are wrong, you want high recall.

Skip connections help ResNet learn deeper features, improving both precision and recall by reducing errors from too shallow or too deep layers.

Good vs Bad metric values for ResNet

Good: Accuracy above 90%, balanced precision and recall near 90% or more, and stable training loss showing skip connections help learning.

Bad: Accuracy stuck around 50-60%, big gap between training and validation loss (overfitting), or very low recall meaning the model misses many true cases.

Common pitfalls in metrics with ResNet and skip connections

• Accuracy paradox: High accuracy but poor recall if data is unbalanced.
• Ignoring training vs validation loss differences can hide overfitting.
• Not checking if skip connections are correctly implemented can cause training to fail silently.
• Data leakage can inflate metrics falsely.

Self-check question

Your ResNet model has 98% accuracy but only 12% recall on the cat class. Is it good for production? Why or why not?

Answer: No, it is not good. The model misses most cats (low recall), so it fails to find many true cats even if overall accuracy looks high. This means it is unreliable for detecting cats.

Key Result

Skip connections in ResNet improve training stability and accuracy by enabling better gradient flow, reflected in balanced precision and recall.