Simple Open-Vocabulary Object Detection with Vision Transformers — HN submission

Sun, 02 Oct 2022 14:48:49 GMT

Show HN: Zero-shot object detection demo

Hello HN! We've built an interactive demo of Google AI's OWL-ViT [1] zero-shot object detection model, using Hugging Face transformers. Regular object detection models are trained on a fixed set of categories, for example cats, dogs and birds. If you want to detect a new type of object, like a horse, you have to collect and label images with horses and retrain your model. A zero-shot object detection model is a so-called open-vocabulary model: it can detect a huge number of object categories without needing to retrain it. These categories are not predefined: you can provide any free-form text…

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple Open-Vocabulary Object Detection with Vision Transformers — HN submission

Sat, 06 Aug 2022 13:52:59 GMT

Simple Open-Vocabulary Object Detection with Vision Transformers

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Simple Open-Vocabulary Object Detection with Vision Transformers · HackerPapers discussions

Simple Open-Vocabulary Object Detection with Vision Transformers — HN submission

Simple Open-Vocabulary Object Detection with Vision Transformers — HN submission