💡 Remember Box – Telegram

💡 Remember Box

10 subscribers

2.1K photos

27 videos

1.8K files

11K links

📝 Interesting articles
🗞 Ideas & Todo💡
👓 Random stuff
🎶 Music
🤔 Thoughts
📕 Books
📚 Courses
📺 Videos
📝 Papers
🕸 Websites/Blogs
🎙 Podcasts
🍄 Spirituality

In the pursuit of excellence!

The aim is to discover interesting ideas and perspectives.

Download Telegram

About

Blog

Apps

Platform

💡 Remember Box

💡 Remember Box

[2311.06242] Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
https://arxiv.org/abs/2311.06242

Florence-2: Advancing a Unified Representation for a Variety of...

We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models...

4 views21:27

💡 Remember Box

[2408.00714] SAM 2: Segment Anything in Images and Videos
https://arxiv.org/abs/2408.00714

SAM 2: Segment Anything in Images and Videos

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user...

4 views21:28

💡 Remember Box

Florence 2 + SAM 2

4 views21:28

💡 Remember Box

💡 Remember Box

Florence 2 + SAM 2

UniFormer with MiT-B0 + LLaVA

4 viewsedited 21:40

💡 Remember Box

YOLO-World + EfficientSAM

4 views21:41

💡 Remember Box

Deformable DETR with MiT-B0 + LLaVA

4 views21:41

💡 Remember Box

Grounding DINO + FastSAM

4 views21:41

💡 Remember Box

COCO test-dev Benchmark (Object Detection) | Papers With Code
https://paperswithcode.com/sota/object-detection-on-coco?p=grounding-dino-marrying-dino-with-grounded

Papers with Code - COCO test-dev Benchmark (Object Detection)

The current state-of-the-art on COCO test-dev is Co-DETR. See a full comparison of 257 papers with code.

4 views21:42

💡 Remember Box

https://github.com/IDEA-Research/Grounded-SAM-2

GitHub - IDEA-Research/Grounded-SAM-2: Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and…

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2 - IDEA-Research/Grounded-SAM-2

4 views21:42

💡 Remember Box

https://github.com/anenbergb/Co-DETR-TensorRT

GitHub - anenbergb/Co-DETR-TensorRT: Co-DETR (Detection Transformer) compiled from PyTorch to NVIDIA TensorRT

Co-DETR (Detection Transformer) compiled from PyTorch to NVIDIA TensorRT - anenbergb/Co-DETR-TensorRT

4 views21:44

💡 Remember Box

💡 Remember Box

Grounding DINO + FastSAM

https://github.com/IDEA-Research/Grounded-Segment-Anything

GitHub - IDEA-Research/Grounded-Segment-Anything: Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion…

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything - IDEA-Research/Grounded-S...

4 views21:47

💡 Remember Box

https://github.com/IDEA-Research/Grounded-SAM-2

GitHub - IDEA-Research/Grounded-SAM-2: Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and…

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2 - IDEA-Research/Grounded-SAM-2

5 views21:48

💡 Remember Box

💡 Remember Box pinned «https://github.com/IDEA-Research/Grounded-SAM-2»

21:49

💡 Remember Box

Florence-2 (~50M), Grounding DINO (~40M), SAM-2 (~30M), totaling ~120M parameters, much larger than Grounding DINO + FastSAM (~10M)

5 views21:59

💡 Remember Box

💡 Remember Box

Grounding DINO + FastSAM

Grounding DINO + FastSAM + LLaVA

5 views22:01

💡 Remember Box

Accuracy (IoU for semantic segmentation, mAP for instance detection, area error)Speed (inference time for a 256x256 image)Model Size (parameters, disk space, GPU memory)Building Code Compliance (ability to exclude non-habitable spaces and apply code rules)Label Processing (text recognition accuracy and integration)Complexity (ease of implementation, number of models, etc.)

5 views22:02

💡 Remember Box

https://github.com/IDEA-Research/Grounded-Segment-Anything/blob/main/EfficientSAM%2FREADME.md

Grounded-Segment-Anything/EfficientSAM/README.md at main · IDEA-Research/Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything - IDEA-Research/Grounded-S...

5 views22:11

💡 Remember Box

LayoutLMv3
https://huggingface.co/docs/transformers/en/model_doc/layoutlmv3

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

7 views22:17

💡 Remember Box

💡 Remember Box

Grounding DINO + FastSAM + LLaVA

+ DSPy

5 views22:43

💡 Remember Box

Segmenting satellite images using SAM and Grounding DINO | Echo Blog
https://www.echo-analytics.com/blog/segmenting-satellite-images-using-sam-and-grounding-dino

Segmenting satellite images using SAM and Grounding DINO | Echo Blog

Read about segmenting satellite images using SAM and Grounding DINO for our data product, Shapes.

6 views22:51