Using Segment-Anything and CLIP to generate pixel-aligned semantic features.
-
Updated
Apr 27, 2023 - Python
Using Segment-Anything and CLIP to generate pixel-aligned semantic features.
use SAM and OpenCLIP to perform zero-shot object detection using COCO 2017 val split.
CLIP based Zero Shot Instance Segmentation
Group images by provided labels using OpenAI/CLIP
Clipora is a powerful toolkit for fine-tuning OpenCLIP models using Low Rank Adapters (LoRA).
Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)
Searching Images: From Clip And Beyond
A goal-oriented planning to lift VLN performance for Closed-Loop Navigation: Simple, Yet Effective
Text-to-image search with OpenCLIP, Docker, Flask, Faiss, etc. and a basic front-end.
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
Add a description, image, and links to the openclip topic page so that developers can more easily learn about it.
To associate your repository with the openclip topic, visit your repo's landing page and select "manage topics."