The base model worked well before.
After fine-tuning on new data, accuracy drops everywhere.
Even old categories are misclassified.
The model seems to have forgotten what it knew.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
The base model worked well before.
After fine-tuning on new data, accuracy drops everywhere.
Even old categories are misclassified.
The model seems to have forgotten what it knew.
This happens because of catastrophic forgetting. When fine-tuned on new data, neural networks overwrite weights that were important for earlier knowledge.
Without constraints, gradient updates push the model to fit the new data at the cost of old patterns. This is especially common when the new dataset is small or biased.
Using lower learning rates, freezing early layers, or mixing old and new data during training reduces this problem.