Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Interfaze: A new model architecture built for high accuracy at scale

interfaze.ai

Post reply on HN
Print view View original

21–30 of 47 posts

Re: Interfaze: A new model architecture built for high accuracy at scale

#21

Post by AnthonyR »

schanz wrote: post #19

Amazing! I just tried the OCR capabilities with a photo of a DIN A4 page which was written with a typewriter. The image isn't the easiest to interpret. The text perspective is distorted because the page is part of a book and the page margin toward the spine of the book is very small. There are also many inline corrections due to typing errors while the page was written (backspace couldn't erase characters back then,…

Have you tried this task using an actual OCR model like Google Cloud Vision AI? I am not sure if this is what Gemini uses under the hood but multi-modal LLMs are not designed to extract text like this so it should be no surprise it's not good at it?

Re: Interfaze: A new model architecture built for high accuracy at scale

#24

Post by yoeven »

schanz wrote: post #19

Amazing! I just tried the OCR capabilities with a photo of a DIN A4 page which was written with a typewriter. The image isn't the easiest to interpret. The text perspective is distorted because the page is part of a book and the page margin toward the spine of the book is very small. There are also many inline corrections due to typing errors while the page was written (backspace couldn't erase characters back then,…

Yup run task mode runs a much smaller part of the model when can drop quality of scans. The issue with run task we have to figure out is how much of the model is needed just for OCR and how to activate the right parts. A lot more improvements coming here with the same cost reduction.

I'd be happy to test it against your sample and see how we can get good results at a lower per page cost. Feel free to email me yoeven@interfaze.ai

Re: Interfaze: A new model architecture built for high accuracy at scale

#26

Post by yoeven »

AnthonyR wrote: post #21
schanz wrote: post #19

Amazing! I just tried the OCR capabilities with a photo of a DIN A4 page which was written with a typewriter. The image isn't the easiest to interpret. The text perspective is distorted because the page is part of a book and the page margin toward the spine of the book is very small. There are also many inline corrections due to typing errors while the page was written (backspace couldn't erase characters back then,…

Have you tried this task using an actual OCR model like Google Cloud Vision AI? I am not sure if this is what Gemini uses under the hood but multi-modal LLMs are not designed to extract text like this so it should be no surprise it's not good at it?

Google Cloud Vision AI is a specialized model built on CNNs frameworks which is part of the Interfaze architecture which is an hybrid so you get best of both worlds. Google cloud vision was pretty far behind other specalized models like PaddleOCR etc anyways so if you're looking for a pure CNN, check them out.

You can find the explanation and the comparison in the article, which we benchmarked pure CNN models, pure LLM models and a hybrid architecture like ours.

Re: Interfaze: A new model architecture built for high accuracy at scale

#28

Post by yoeven »

fraywing wrote: post #15

So is this basically a task-specific MoA transformer arch with a DNN that helps make routing decisions? Trying to understand this.

The other way round, task specific DNNs adapted to share the same vector space as omni-transformers with generalized vision, audio encoders.

E.g. For an OCR task, the first pass will be handled by the CNN, converted to shared tokens which the transformer can consume, correct any issues if needed and a decoder that can handle both the DNN and transformer output.

Re: Interfaze: A new model architecture built for high accuracy at scale

#29

Post by yoeven »

icemaze wrote: post #16

Great in the benchmarks but not as good in the real world, sorry to say. Just gave it a try in my STT bot, it's worse than whisper

Use it run task mode if you're doing a one to one comparison to whisper, it's going to be a lot faster too.

Here's a good example: https://interfaze.ai/docs/audio/speech-to-text#long-audio-tr...

Re: Interfaze: A new model architecture built for high accuracy at scale

#30

Post by yoeven »

philipkglass wrote: post #18
florians wrote: post #17

What I want are precise and tight bounding boxes. Why is this so difficult?

The PP-DocLayoutV3 [1] bounding boxes are pretty good in my experience, if you want boxes around individual document headings or paragraphs. If you want boxes around individual words, similar to what's shown in the Interfaze screen shot [2], Apple has a LiveText "token" model that's proprietary but free/bundled with macOS and iOS. There are easy to use Python bindings here: https://github.com/straussmaximilian/ocrmac…

For sure there a tons of OCR bounding models and tons of other models like SAM 3 for segmentation.

Interfaze is a more powerful version of them combined into a single model, you can run multi turn tasks like extract all the text and object from this document then translate or generate a report.

It's like getting the best of both worlds from pure DNN/CNN models like Paddle and the flexibility and nuace of an LLM while outperforming both in accuracy.

Post reply on HN