Update README.md

README.md

@@ -1,9 +1,11 @@
 ---
 library_name: transformers
-tags: []
+license: apache-2.0
+pipeline_tag: image-segmentation
 ---
 
-# Model Card for Model ID
+# Model Card for SAM 2: Segment Anything in Images and Videos
+
 
 <!-- Provide a quick summary of what the model is/does. -->
 
@@ -13,25 +15,25 @@ tags: []
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+SAM 2 (Segment Anything Model 2) is a foundation model developed by Meta FAIR for promptable visual segmentation across both images and videos. It extends the capabilities of the original SAM by introducing a memory-driven, streaming architecture that enables real-time, interactive segmentation and tracking of objects even as they change or temporarily disappear across video frames. SAM 2 achieves state-of-the-art segmentation accuracy with significantly improved speed and data efficiency, outperforming existing models for both images and videos.
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** Meta FAIR (Meta AI Research), Authors: Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, Christoph Feichtenhofer.
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
+- **Model type:** Transformer-based promptable visual segmentation model with streaming memory module for videos.
 - **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
+- **License:** Apache-2.0, BSD 3-Clause
 - **Finetuned from model [optional]:** [More Information Needed]
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://github.com/facebookresearch/sam2
+- **Paper [optional]:** https://arxiv.org/abs/2408.00714
+- **Demo [optional]:** https://ai.meta.com/sam2/
 
 ## Uses
 
@@ -39,9 +41,15 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+SAM 2 is designed for:
 
-[More Information Needed]
+Promptable segmentation—select any object in video or image using points, boxes, or masks as prompts.
+
+Zero-shot segmentation—performs strongly even on objects, image domains, or videos not seen during training.
+
+Real-time, interactive applications—track or segment objects across frames, allowing corrections/refinements with new prompts as needed.
+
+Research and industrial applications—facilitates precise object segmentation in video editing, robotics, AR, medical imaging, and more.
 
 ### Downstream Use [optional]
 
@@ -57,15 +65,15 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+Generalization Limits: While designed for zero-shot generalization, rare or unseen visual domains may challenge model reliability.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Human-in-the-loop review is advised for critical use cases.
+
+Users should evaluate and possibly retrain or fine-tune SAM 2 for highly specific domains.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Ethical and privacy considerations must be taken into account, especially in surveillance or sensitive settings.
 
 ## How to Get Started with the Model
 
@@ -77,13 +85,15 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+Trained using a data engine that collected the largest known video segmentation dataset, SA-V (Segment Anything Video dataset), via interactive human-model collaboration.
 
-[More Information Needed]
+Focused on full objects and parts, not restricted by semantic classes.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Preprocessing: Images and videos processed into masklets (spatio-temporal masks); prompts collected via human and model interaction loops.
+
+Training regime: Used standard transformer training routines with enhancements for real-time processing; likely mixed precision for scaling to large datasets.
 
 #### Preprocessing [optional]
 
@@ -108,9 +118,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
+Evaluated on SA-V and other standard video and image segmentation benchmarks.
 
 #### Factors
 
@@ -120,13 +128,17 @@ Use the code below to get started with the model.
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+Segmentation accuracy (IoU, Dice).
 
-[More Information Needed]
+Prompt efficiency (number of user interactions to achieve target quality).
+
+Speed/Throughput (frames per second).
 
 ### Results
 
-[More Information Needed]
+Video segmentation: Higher accuracy with 3x fewer user prompts versus prior approaches.
+
+Image segmentation: 6x faster and more accurate than original SAM.
 
 #### Summary
 
@@ -174,11 +186,16 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 **BibTeX:**
 
-[More Information Needed]
+@article{ravi2024sam2,
+  title={SAM 2: Segment Anything in Images and Videos},
+  author={Nikhila Ravi and Valentin Gabeur and Yuan-Ting Hu and Ronghang Hu and Chaitanya Ryali and Tengyu Ma and Haitham Khedr and Roman R{\"a}dle and Chloe Rolland and Laura Gustafson and Eric Mintun and Junting Pan and Kalyan Vasudev Alwala and Nicolas Carion and Chao-Yuan Wu and Ross Girshick and Piotr Doll\'ar and Christoph Feichtenhofer},
+  journal={arXiv preprint arXiv:2408.00714},
+  year={2024}
+}
 
 **APA:**
 
-[More Information Needed]
+Ravi, N., Gabeur, V., Hu, Y.-T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rolland, C., Gustafson, L., Mintun, E., Pan, J., Alwala, K. V., Carion, N., Wu, C.-Y., Girshick, R., Dollár, P., & Feichtenhofer, C. (2024). SAM 2: Segment Anything in Images and Videos. arXiv preprint arXiv:2408.00714.
 
 ## Glossary [optional]
 
@@ -192,8 +209,8 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Authors [optional]
 
-[More Information Needed]
+[Sangbum Choi](https://www.linkedin.com/in/daniel-choi-86648216b/) and [Yoni Gozlan](https://huggingface.co/yonigozlan)
 
 ## Model Card Contact
 
-[More Information Needed]
+Meta FAIR (contact via support@segment-anything.com)