News for hackers. Stuff that matters.
Re:Coping with dumb LLMs using classic ML by whiplash451 on Friday January 24, 2025 @10:19AM (#42813905)
1. You need to look into the OCR-specific literature of DL (e.g. udop) or segmentation-based (e.g. segment-anything)

2. BigTech and SmallTech train their fancy bounding box / detection models on large datasets that have been built using classical detectors and a ton of manual curation

There are no comments on this comment yet.