News for hackers. Stuff that matters.
Re:DeepSeek Introduces Vision by bigmadshoe on Thursday June 18, 2026 @02:30PM (#48589483)
I agree, but since we're talking about imagine understanding with text output, clearly a CNN is unsuitable. My previous comment was overly reductive and CNNs can still be SoTA depending on your performance metrics. I spent the earlier part of my career training CNNs, and they are very pleasant to work with.
Re:DeepSeek Introduces Vision by bonoboTP on Thursday June 18, 2026 @06:11PM (#48592338)
You can run a CNN and use the downsampled feature map the same way as patch tokens.