The OWL-ViT model currently supports image-guided one-shot object detection by using reference image embeddings as the input to the classification head instead of the text embedding. This is implemented by the image_guided_detection method. There are 2 problems it doesn’t support passing multiple…

Caching image prototype embeddings for image-guided object detection using OWL-ViT

taher30 April 11, 2025, 7:59pm 2

Did you happen to get a solution or alternative for this? I am trying to do something similar.

1 Like

Topic		Replies	Views
OwlV2 significantly slower than OwlVit 🤗Transformers	0	581	February 14, 2024
Using Owl ViT Embeddings with cosine similarity 🤗Transformers	1	567	February 15, 2024
Owl-vit batch images inference Beginners	2	1142	May 7, 2024
Failling fine-tuning OWL-ViT Beginners	4	2771	April 11, 2023
Adding a New tokens to ViT 🤗Transformers	0	295	March 10, 2023