💡 Remember Box
Grounding DINO + FastSAM
GitHub
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...
Florence-2 (~50M), Grounding DINO (~40M), SAM-2 (~30M), totaling ~120M parameters, much larger than Grounding DINO + FastSAM (~10M)
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.)
Segmenting satellite images using SAM and Grounding DINO | Echo Blog
https://www.echo-analytics.com/blog/segmenting-satellite-images-using-sam-and-grounding-dino
https://www.echo-analytics.com/blog/segmenting-satellite-images-using-sam-and-grounding-dino
Echo-Analytics
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.
Why is quality so rare? - Linear Blog
https://linear.app/blog/why-is-quality-so-rare
https://linear.app/blog/why-is-quality-so-rare
linear.app
Why is quality so rare? - Linear Blog
[1706.02216] Inductive Representation Learning on Large Graphs
https://arxiv.org/abs/1706.02216
https://arxiv.org/abs/1706.02216
arXiv.org
Inductive Representation Learning on Large Graphs
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most...
[2505.13447] Mean Flows for One-step Generative Modeling
https://arxiv.org/abs/2505.13447
https://arxiv.org/abs/2505.13447
arXiv.org
Mean Flows for One-step Generative Modeling
We propose a principled and effective framework for one-step generative modeling. We introduce the notion of average velocity to characterize flow fields, in contrast to instantaneous velocity...