Detic VS clip-fields

Some of the foundation/base models include: * GroundedSAM (Segment Anything Model) * DETIC * GroundingDINO

For localisation at search time I ended up using OWL-ViT. This worked really well. I did not try Detic or CLIPseg but would be interested to hear if anyone else has tried these?

git clone https://github.com/facebookresearch/Detic cd Detic pip install -r requirements python demo.py --config-file configs/Detic_LCOCOI21k_CLIP_SwinB_896b32_4x_ft4x_max-size.yaml --input desk.jpg --output out.jpg --vocabulary lvis --opts MODEL.WEIGHTS models/Detic_LCOCOI21k_CLIP_SwinB_896b32_4x_ft4x_max-size.pth

You might want to take a look at DETIC : https://github.com/facebookresearch/Detic (Open Vocabulary Object Detection, trained on thousands of classes)

Are there any open-label segmentation model included in this repo, like Detic or LSeg?

We made this using pretty recent advances in web-data pretrained models like Detic and LSeg for detection, CLIP for visual queries, and Sentence BERT for semantic queries. Our "database" is really a neural field (Instant NGP) that maps from 3D coordinates to a high dimensional embedding vector in the same representation space as CLIP and SBERT.

Is it similar to the open vocabulary detic?

Code for https://arxiv.org/abs/2201.02605 found: https://github.com/facebookresearch/Detic

github: https://github.com/facebookresearch/Detic

Best part, I believe, is that you should be able to train your own CLIP-Field for your living room if you have an hour, a decent GPU, and a way to get RGB-D video (an iPhone 13 Pro works great!) I hope you can give the code a try: https://github.com/notmahi/clip-fields or check out the website https://mahis.life/clip-fields/ for more interactive demos. Our Arxiv submission is also out now, at https://arxiv.org/abs/2210.05663, and if you want a longer tl;dr with a couple more videos, check out this tweet. Thanks!