search

lidq92 / MDTVSFA

[official] Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training (IJCV 2021)
MIT License
83 stars 16 forks source link

Consider an end-to-end network？ #2

Closed ciwei123 closed 3 years ago

ciwei123 commented 3 years ago

@lidq92 Thanks for your sharing. I found that 'CNN_feature_extract' and 'regression_score' are carried out separately during the training. Have you considered an end-to-end network? That means training the ‘CNN_feature_extract’ network. I want to know if it is necessary to train the feature extraction part.Thank you very much!!

lidq92 commented 3 years ago

@ciwei123 It will take too many computing resources.

One possible way to update the feature extraction module is that fine-tuning it with IQA datasets.