Update README.md

README.md

@@ -5,6 +5,6 @@ pipeline_tag: image-classification
 
 A tiny 230K param, opinionated image compression classifier. CNN. Trained on JPEG, JXL, AVIF, WEBP and PNG. Hits 94.3% accuracy on the task.
 
-Attempts to flags images below q=80 for JPEG and below 65 for the rest. This was driven by a paper showing image models trained on a lot of q=75 had massive performance penalties.
+Attempts to flags images below q=80 for JPEG and below 65 for the rest. This was driven by research showing image models trained on many q=75 JPEGS had massive performance penalties.
 
 Training was 128x128 patches + multi-scale high freq residuals. DCT aware 8x8 stem and dual heads (binary acceptable/not + codec classifier).