[HN Gopher] PaliGemma 2: Powerful Vision-Language Models, Simple...
       ___________________________________________________________________
        
       PaliGemma 2: Powerful Vision-Language Models, Simple Fine-Tuning
        
       Author : meetpateltech
       Score  : 112 points
       Date   : 2024-12-05 17:46 UTC (5 hours ago)
        
 (HTM) web link (developers.googleblog.com)
 (TXT) w3m dump (developers.googleblog.com)
        
       | minimaxir wrote:
       | Hugging Face's blog post on the release is more technical:
       | https://huggingface.co/blog/paligemma2
        
         | xnx wrote:
         | Even more technical detail here:
         | https://arxiv.org/html/2412.03555v1
        
       | dmvdoug wrote:
       | Saw name, was expecting something to do with wreaking AI upon the
       | Pali Canon (https://en.m.wikipedia.org/wiki/Pali_Canon).
        
       | turnsout wrote:
       | Does anyone know how this stacks up against other multimodal
       | vision models?
        
         | mountainriver wrote:
         | They do an exceptionally poor job at evaluating it against
         | competitors.
        
       | exe34 wrote:
       | does anyone know if they can output bonding box coordinates? like
       | "where is the ball" -> [50, 75, 150, 175].
       | 
       | so far cogvlm is the only one I've seen that works but it's a bit
       | of a pain to run.
        
         | xnx wrote:
         | Yes: "The initial four location tokens represent the coordinate
         | of the bounding box, ranging from 0 to 1023. These coordinates
         | are independent of the aspect ratio, as the image is assumed to
         | be resized to 1024 x 1024."
         | 
         | https://developers.googleblog.com/en/gemma-explained-paligem...
        
           | exe34 wrote:
           | Thank you! Will have a play with that.
        
         | __jl__ wrote:
         | Gemini is surprisingly good at this. Look at example 5 here:
         | https://developers.googleblog.com/en/7-examples-of-geminis-m...
         | 
         | They also have a colab notebook with more examples linked in
         | the article.
        
           | exe34 wrote:
           | I meant weights-available ones, but thank you!
        
       | sigmar wrote:
       | It is probably hard to come up with good benchmarks for VLMs like
       | this, but I feel like the "Non entailment sentences" benchmark
       | seems ill-suited. The examples for sentences that were non
       | entailment included[1]: "There is a pile of horse manure in front
       | of the horse." Which is true if you mean "in front of the
       | [photosubject] from the perspective of the camera," but I think
       | they marked it as non entailment because the pile is not in front
       | of the horse's face(?)
       | 
       | [1] page 20 https://arxiv.org/pdf/2412.03555
        
       | timmg wrote:
       | I recently wanted to try to get an LLM to help me organize my
       | photos. (I'm someone who takes a lot of photos when I travel and
       | then back them up to a hard drive -- assuming someday I'll
       | organize them :)
       | 
       | I created a prompt to try to get an LLM to do high-level
       | organization:
       | 
       | > Help categorize this photo for organization. Please output in
       | JSON.
       | 
       | > First, add a field called "type" that is one of: Wildlife,
       | Architecture, Landscape, People or other. Pick the one that most
       | appropriately reflects the subject of the photo. Use Other if you
       | don't feel confident in your answer.
       | 
       | > Next, if it is Wildlife, please add another field called
       | "animal" that gives a general type of animal that is the focus of
       | the photo. Use large, common types like Elephant, Bird, Lion,
       | Fish, Antelope, etc. Do not add this field if your confidence is
       | low.
       | 
       | > If the type of animal is Bird, add a field called "bird" that
       | gives the common type of bird, if you can clearly determine it.
       | For example: Eagle, Hummingbird, Vulture, Crow, etc.
       | 
       | > If it is an Architecture photo, and you can determine with good
       | confidence what specific building (or city) it is a photo of,
       | please add a field called "place" with that name. (Name only,
       | please -- no description).
       | 
       | I've tried with llama-vision using Ollama and it worked
       | reasonably well for the top-level categories. A little less-well
       | for identifying specific birds or places. And it didn't always
       | generate proper JSON (and sometimes added new fields to JSON.)
       | 
       | I also tried with Claude's API -- and it seemed to work perfectly
       | (for a small sample size).
       | 
       | It will be interesting to try with PaliGemma and see what I get.
       | 
       | I have like 50k photos, so I don't want to pay $$$ for the Claude
       | API to categorize them all. It will be cool someday (soon?) for
       | an open-source DAM to have something like one of these models
       | available to call locally.
        
         | visarga wrote:
         | use the json mode in ollama
        
         | senko wrote:
         | Simonw estimates it'd cost less than $10 to categorize 67k+
         | photos using Amazon Nova:
         | https://simonwillison.net/2024/Dec/4/amazon-nova/#gamoa
         | 
         | I agree it'll still be cool to be able to do it all locally.
        
         | rsolva wrote:
         | The photo organizing software Ente [0] can do this, and is
         | packaged into a really neat product. I have not gotten around
         | to try the self hosted version yet, but it is on my list!
         | 
         | [0] https://ente.io/ml
        
       ___________________________________________________________________
       (page generated 2024-12-05 23:00 UTC)