Detic VS LAVIS

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

For multimodal, there's China (*many), then Salesforce.

Been trying for all day to get a working inference for this example: https://github.com/salesforce/LAVIS/tree/main/projects/instructblip

There's also been big breakthroughs in computer vision. Not that long ago it was hard to recognize if a photo contained a bird; that's solved now by models like CLIP, Yolo, or Segment Anything. Now research has moved on to generating 3D scenes from images or interactively answering questions about images.

The new hotness is multimodal vision-language models like InstructBLIP that can interactively answer questions about images. Check out the examples in the github repo, I would not have thought this was possible a few years ago.

Salesforce’s BLIP family has a new member– InstructBLIP, a vision-language instruction-tuning framework using BLIP-2 models. It has achieved state-of-the-art zero-shot generalization performance on a wide range of vision-language tasks, substantially outperforming BLIP-2 and Flamingo. (Source)

Github

Most of my workflows are self-made. For captioning I used Blip-2 in a custom script I made that automates the process by going into directories and their sub-directories and creates a .txt file beside each image. This way I can keep my images organized in their proper directories, without having to put dump them all in a single place.