Hacker News with Generative AI: Image Recognition

Watching o3 guess a photo's location is surreal, dystopian and entertaining (simonwillison.net)
Watching OpenAI’s new o3 model guess where a photo was taken is one of those moments where decades of science fiction suddenly come to life. It’s a cross between the Enhance Button and Omniscient Database TV Tropes.

Artificial Intelligence, Image Recognition, Technology, Computer Vision, Science Fiction

987 points by simonw 188 days ago | 433 comments

Viral ChatGPT trend is doing 'reverse location search' from photos (techcrunch.com)
There’s a somewhat concerning new trend going viral: People are using ChatGPT to figure out the location shown in pictures.

ChatGPT, Privacy Concerns, Artificial Intelligence, Image Recognition

108 points by jnord 196 days ago | 55 comments

ChatGPT models are surprisingly good at Geoguessing (techcrunch.com)
There’s a somewhat concerning new trend going viral: People are using ChatGPT to figure out the location shown in pictures.

Generative AI, Artificial Intelligence, ChatGPT, Social Media, Image Recognition

11 points by coloneltcb 197 days ago | 0 comments

Self-Supervised Learning from Images with JEPA (2023) (arxiv.org)
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations.

Self-Supervised Learning, Computer Vision, Image Recognition, Artificial Intelligence, Deep Learning

40 points by Brysonbw 216 days ago | 10 comments

Ask HN: Anyone pursuing this AI image idea (images to list of insured losses)? (ycombinator.com)
The idea is for AI to interpret photos and videos and create a detailed and accurate list of exactly what was lost, so claimants can collect the full value of their insured losses.

Artificial Intelligence, Insurance, Business Ideas, Image Recognition

13 points by mgav 266 days ago | 15 comments

Generating image descriptions and alt-text with AI (dri.es)
I tested 12 LLMs — 10 running locally and 2 cloud-based — to assess their accuracy in generating alt-text for images.

Generative AI, Artificial Intelligence, Image Recognition, Accessibility

3 points by todsacerdoti 270 days ago | 0 comments

Homomorphic encryption in iOS 18 (boehs.org)
You are Apple. You want to make search work like magic in the Photos app, so the user can find all their “dog” pictures with ease. You devise a way to numerically represent the concepts of an image, so that you can find how closely images are related in meaning. Then, you create a database of known images and their numerical representations (“this number means car”), and find the closest matches. To preserve privacy, you put this database on the phone.

Privacy, Image Recognition, Security

377 points by surprisetalk 293 days ago | 214 comments

How we used GPT-4o for image detection with 350 similar illustrations (pages.dev)

Generative AI, Image Recognition

222 points by olup 293 days ago | 90 comments

Homomorphic Encryption in iOS 18 (boehs.org)
You are Apple. You want to make search work like magic in the Photos app, so the user can find all their “dog” pictures with ease. You devise a way to numerically represent the concepts of an image, so that you can find how closely images are related in meaning. Then, you create a database of known images and their numerical representations (“this number means car”), and find the closest matches. To preserve privacy, you put this database on the phone.

Privacy, Mobile Security, Machine Learning, Image Recognition, iOS

10 points by vsgherzi 294 days ago | 0 comments

Show HN: Pixie – A tool to shop for clothes using pictures (ShopWithPixie.com)

Shopping, Image Recognition, Tools, E-commerce, Fashion

13 points by dayaya 298 days ago | 4 comments

Apple auto-opts everyone into having their photos analyzed by AI for landmarks (theregister.com)
Apple last year deployed a mechanism for identifying landmarks and places of interest in images stored in the Photos application on its customers iOS and macOS devices and enabled it by default, seemingly without explicit consent.

Privacy, Apple, AI, Image Recognition

90 points by pseudolus 301 days ago | 54 comments

DreamSim: Learning New Dimensions of Human Visual Similarity (2023) (dreamsim-nights.github.io)
Which image, A or B, is most similar to the reference? We generate a new benchmark of synthetic image triplets that span a wide range of mid-level variations, labeled with human similarity judgments.

Computer Vision, Image Recognition, Machine Learning, Artificial Intelligence

10 points by lnyan 343 days ago | 0 comments

Pixtral Large (mistral.ai)
Today we announce Pixtral Large, a 124B open-weights multimodal model built on top of Mistral Large 2. Pixtral Large is the second model in our multimodal family and demonstrates frontier-level image understanding.

Generative AI, Open Source, Image Recognition

15 points by sshroot 347 days ago | 1 comments

Claude can now view images within a PDF (twitter.com)

Artificial Intelligence, Image Recognition

8 points by timbilt 364 days ago | 2 comments

Implementing neural networks on the "3 cent" 8-bit microcontroller (wordpress.com)
Bouyed by the surprisingly good performance of neural networks with quantization aware training on the CH32V003, I wondered how far this can be pushed. How much can we compress a neural network while still achieving good test accuracy on the MNIST dataset?

Neural Networks, Machine Learning, Microcontrollers, Embedded Systems, Image Recognition

159 points by cpldcpu 377 days ago | 20 comments

Kagi Update: AI Image Filter for Search Results (kagi.com)
As AI-generated images become increasingly prevalent across the web, many users find their image search results cluttered with artificial content. This can be particularly frustrating when searching for authentic, human-created images or specific real-world references.

AI, Search Engines, Image Recognition, Privacy

271 points by lkellar 378 days ago | 105 comments

Answer any question about your photo albums with OmniQuery (jiahaoli.net)
OmniQuery enables free-form question answering on personal memories (i.e., private data in albums) with RAG. Specifically, it applies contextual data augmentation (taxonomy-based) to enhance the retrieval accuracy, and uses LLMs to generate answers based on the retrieved memory instances.

Artificial Intelligence, Image Recognition, Computer Vision, Personal Data, Privacy

51 points by ljhnick 388 days ago | 14 comments

Can you tell if these images are real or generated? (britannicaeducation.com)

Artificial Intelligence, Image Generation, Image Recognition, Computer Vision

26 points by smusamashah 466 days ago | 37 comments

Show HN: Cluttr – A local first utility to make images searchable using Ollama (cluttr.ai)

Search Engines, Artificial Intelligence, Open Source, Web Development, Image Recognition

11 points by bearjaws 469 days ago | 1 comments

Ultra simplified "MNIST" in 60 lines of Python with NumPy (github.com/tonio-m)

Machine Learning, Python, NumPy, Image Recognition

37 points by tonio 477 days ago | 6 comments

Google's Nonconsensual Explicit Images Problem Is Getting Worse (wired.com)