From d0b1b9d5aafeac07e893ab87e002eaaaa7381802 Mon Sep 17 00:00:00 2001 From: "Eric O. Korman" Date: Fri, 21 Nov 2025 16:54:07 -0800 Subject: [PATCH] Fix SA-CO benchmark link in README (#149) Summary: Updated the link for the SA-CO benchmark in the README. Pull Request resolved: https://github.com/facebookresearch/sam3/pull/149 Reviewed By: chayryali Differential Revision: D87675994 Pulled By: haithamkhedr fbshipit-source-id: 22b8fb823b72013ad7e77952a9b25b43ad6d4df9 --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 709f872..b9d310b 100644 --- a/README.md +++ b/README.md @@ -46,7 +46,7 @@ Meng Wang, [Peize Sun](https://peizesun.github.io/), [[`Blog`](https://ai.meta.com/blog/segment-anything-model-3/)] -![SAM 3 architecture](assets/model_diagram.png?raw=true) SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. Compared to its predecessor [SAM 2](https://github.com/facebookresearch/sam2), SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase or exemplars. Unlike prior work, SAM 3 can handle a vastly larger set of open-vocabulary prompts. It achieves 75-80% of human performance on our new [SA-CO benchmark](https://github.com/facebookresearch/sam3/edit/main_readme/README.md#sa-co-dataset) which contains 270K unique concepts, over 50 times more than existing benchmarks. +![SAM 3 architecture](assets/model_diagram.png?raw=true) SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. Compared to its predecessor [SAM 2](https://github.com/facebookresearch/sam2), SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase or exemplars. Unlike prior work, SAM 3 can handle a vastly larger set of open-vocabulary prompts. It achieves 75-80% of human performance on our new [SA-CO benchmark](https://github.com/facebookresearch/sam3?tab=readme-ov-file#sa-co-dataset) which contains 270K unique concepts, over 50 times more than existing benchmarks. This breakthrough is driven by an innovative data engine that has automatically annotated over 4 million unique concepts, creating the largest high-quality open-vocabulary segmentation dataset to date. In addition, SAM 3 introduces a new model architecture featuring a presence token that improves discrimination between closely related text prompts (e.g., “a player in white” vs. “a player in red”), as well as a decoupled detector–tracker design that minimizes task interference and scales efficiently with data.