DeepSeek OCR
github.com
DeepSeek OCR
1–10 of 252 posts
Re: DeepSeek OCR
#2How good is this compared to most commercial OCR software?
Re: DeepSeek OCR
#3This could be great for extracting text from old magazines; traditional OCR gives you a bit of a mess you have to clean up, but this looks like it can properly identify columns and track the flow accurately (and extract images!) It appears it can convert magazine layouts to markdown too
Re: DeepSeek OCR
#4How good is this compared to most commercial OCR software?
Any vision model is better than commercial OCR software.
Re: DeepSeek OCR
#5This looks really cool for prototyping and playing around.
It seems to me though if one is building a modern application that needs to get image segmentation and/or text recognition right there are better APIs available than natural language? It seems like a lot of effort to make a production-scale CV application to weigh it down with all of an LLM’s shortcomings. Not a field I’m familiar with but I would assume that this doesn’t produce state of the art results—that would change the analysis.
Re: DeepSeek OCR
#6This looks really cool for prototyping and playing around. It seems to me though if one is building a modern application that needs to get image segmentation and/or text recognition right there are better APIs available than natural language? It seems like a lot of effort to make a production-scale CV application to weigh it down with all of an LLM’s shortcomings. Not a field I’m familiar with but I would assume that…
Imagine you build an image segmentation model for a e.g. specific industrial application.
With this LLM approach you can at least create your training data from the raw images with natural language.
Re: DeepSeek OCR
#7This looks really cool for prototyping and playing around. It seems to me though if one is building a modern application that needs to get image segmentation and/or text recognition right there are better APIs available than natural language? It seems like a lot of effort to make a production-scale CV application to weigh it down with all of an LLM’s shortcomings. Not a field I’m familiar with but I would assume that…
Imagine you build an image segmentation model for a e.g. specific industrial application. With this LLM approach you can at least create your training data from the raw images with natural language.
That does make sense
Re: DeepSeek OCR
#8The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote
>Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios, while 20× compression still retains 60% accuracy.
(I guess you could say a picture token is worth 10 textual tokens...)
Could someone explain to a noob what the information-theoretic intuition is here? Why does this work, is it that text tokens are still too "granular"/repetitive and don't come close to the ideal entropy coding? Or is switching to vision tokens escaping the limitation of working "one word-ish at a time", allowing you to get closer to entropy (similar to the way that arithmetic encoding does compared to huffman codes)?
And then they start talking about handling long-context by literally(?) downscaling images, forming a correspondence between information loss in the textual domain and the image domain.
Re: DeepSeek OCR
#9Looks great, but looking at the benchmark, can’t help but think about how crazy good dots-ocr is as a model. Too bad they’re not as open as the Deepseek team because its so crazy good and would love to know how it was trained.
Re: DeepSeek OCR
#10The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote >Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios,…
LLMs are compute heavy with quadratic scaling (in compute) per tokens. They are trying to compress text tokens into visual tokens with their VLM.
Maybe they would render texts to an image before tokenizing to reduce the compute cost.