mirror of
https://github.com/ultralytics/ultralytics
synced 2026-05-24 01:28:26 +00:00
Update SAM vs YOLO benchmarks (#19705)
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher
GitHub
parent
376a906dd3
commit
7b2899cdc9
3 changed files with 79 additions and 43 deletions
|
|
@ -52,6 +52,49 @@ This table presents the available models with their specific pre-trained weights
|
|||
| FastSAM-s | [FastSAM-s.pt](https://github.com/ultralytics/assets/releases/download/v8.2.0/FastSAM-s.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ✅ |
|
||||
| FastSAM-x | [FastSAM-x.pt](https://github.com/ultralytics/assets/releases/download/v8.2.0/FastSAM-x.pt) | [Instance Segmentation](../tasks/segment.md) | ✅ | ❌ | ❌ | ✅ |
|
||||
|
||||
## FastSAM Comparison vs YOLO
|
||||
|
||||
Here we compare Meta's SAM 2 models, including the smallest SAM2-t variant, with Ultralytics smallest segmentation model, [YOLO11n-seg](../tasks/segment.md):
|
||||
|
||||
| Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
|
||||
| ---------------------------------------------------------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
|
||||
| [Meta SAM-b](sam.md) | 375 | 93.7 | 49401 |
|
||||
| [Meta SAM2-b](sam-2.md) | 162 | 80.8 | 31901 |
|
||||
| [Meta SAM2-t](sam-2.md) | 78.1 | 38.9 | 25997 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 25381 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 [backbone](https://www.ultralytics.com/glossary/backbone) | 23.7 | 11.8 | 55.9 |
|
||||
| Ultralytics [YOLOv8n-seg](yolov8.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **24.5** (1061x faster) |
|
||||
| Ultralytics [YOLO11n-seg](yolo11.md) | **5.9** (13.2x smaller) | **2.9** (13.4x less) | **30.1** (864x faster) |
|
||||
|
||||
This comparison demonstrates the substantial differences in model sizes and speeds between SAM variants and YOLO segmentation models. While SAM provides unique automatic segmentation capabilities, YOLO models, particularly YOLOv8n-seg and YOLO11n-seg, are significantly smaller, faster, and more computationally efficient.
|
||||
|
||||
Tests run on a 2025 Apple M4 Pro Macbook with 24GB of RAM using `torch==2.6.0` and `ultralytics==8.3.90`. To reproduce this test:
|
||||
|
||||
!!! example
|
||||
|
||||
=== "Python"
|
||||
|
||||
```python
|
||||
from ultralytics import ASSETS, SAM, YOLO, FastSAM
|
||||
|
||||
# Profile SAM2-t, SAM2-b, SAM-b, MobileSAM
|
||||
for file in ["sam_b.pt", "sam2_b.pt", "sam2_t.pt", "mobile_sam.pt"]:
|
||||
model = SAM(file)
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
|
||||
# Profile FastSAM-s
|
||||
model = FastSAM("FastSAM-s.pt")
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
|
||||
# Profile YOLO models
|
||||
for file_name in ["yolov8n-seg.pt", "yolo11n-seg.pt"]:
|
||||
model = YOLO(file_name)
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
```
|
||||
|
||||
## Usage Examples
|
||||
|
||||
The FastSAM models are easy to integrate into your Python applications. Ultralytics provides user-friendly Python API and CLI commands to streamline development.
|
||||
|
|
|
|||
|
|
@ -226,22 +226,23 @@ SAM 2 can be utilized across a broad spectrum of tasks, including real-time vide
|
|||
|
||||
- This example demonstrates how SAM 2 can be used to segment the entire content of an image or video if no prompts (bboxes/points/masks) are provided.
|
||||
|
||||
## SAM 2 comparison vs YOLOv8
|
||||
## SAM 2 Comparison vs YOLO
|
||||
|
||||
Here we compare Meta's smallest SAM 2 model, SAM2-t, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md):
|
||||
Here we compare Meta's SAM 2 models, including the smallest SAM2-t variant, with Ultralytics smallest segmentation model, [YOLO11n-seg](../tasks/segment.md):
|
||||
|
||||
| Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
|
||||
| ---------------------------------------------------------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
|
||||
| [Meta SAM-b](sam.md) | 375 | 93.7 | 161440 |
|
||||
| Meta SAM2-b | 162 | 80.8 | 121923 |
|
||||
| Meta SAM2-t | 78.1 | 38.9 | 85155 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 98543 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 [backbone](https://www.ultralytics.com/glossary/backbone) | 23.7 | 11.8 | 140 |
|
||||
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **79.5** (1071x faster) |
|
||||
| [Meta SAM-b](sam.md) | 375 | 93.7 | 49401 |
|
||||
| Meta SAM2-b | 162 | 80.8 | 31901 |
|
||||
| Meta SAM2-t | 78.1 | 38.9 | 25997 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 25381 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 [backbone](https://www.ultralytics.com/glossary/backbone) | 23.7 | 11.8 | 55.9 |
|
||||
| Ultralytics [YOLOv8n-seg](yolov8.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **24.5** (1061x faster) |
|
||||
| Ultralytics [YOLO11n-seg](yolo11.md) | **5.9** (13.2x smaller) | **2.9** (13.4x less) | **30.1** (864x faster) |
|
||||
|
||||
This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient.
|
||||
This comparison demonstrates the substantial differences in model sizes and speeds between SAM variants and YOLO segmentation models. While SAM provides unique automatic segmentation capabilities, YOLO models, particularly YOLOv8n-seg and YOLO11n-seg, are significantly smaller, faster, and more computationally efficient.
|
||||
|
||||
Tests run on a 2023 Apple M2 Macbook with 16GB of RAM using `torch==2.3.1` and `ultralytics==8.2.82`. To reproduce this test:
|
||||
Tests run on a 2025 Apple M4 Pro Macbook with 24GB of RAM using `torch==2.6.0` and `ultralytics==8.3.90`. To reproduce this test:
|
||||
|
||||
!!! example
|
||||
|
||||
|
|
@ -261,10 +262,11 @@ Tests run on a 2023 Apple M2 Macbook with 16GB of RAM using `torch==2.3.1` and `
|
|||
model.info()
|
||||
model(ASSETS)
|
||||
|
||||
# Profile YOLOv8n-seg
|
||||
model = YOLO("yolov8n-seg.pt")
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
# Profile YOLO models
|
||||
for file_name in ["yolov8n-seg.pt", "yolo11n-seg.pt"]:
|
||||
model = YOLO(file_name)
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
```
|
||||
|
||||
## Auto-Annotation: Efficient Dataset Creation
|
||||
|
|
@ -388,17 +390,6 @@ SAM 2 includes a sophisticated memory mechanism to manage temporal dependencies
|
|||
|
||||
This mechanism ensures continuity even when objects are temporarily obscured or exit and re-enter the scene. For more details, refer to the [Memory Mechanism and Occlusion Handling](#memory-mechanism-and-occlusion-handling) section.
|
||||
|
||||
### How does SAM 2 compare to other segmentation models like YOLOv8?
|
||||
### How does SAM 2 compare to other segmentation models like YOLO11?
|
||||
|
||||
SAM 2 and Ultralytics YOLOv8 serve different purposes and excel in different areas. While SAM 2 is designed for comprehensive object segmentation with advanced features like zero-shot generalization and real-time performance, YOLOv8 is optimized for speed and efficiency in [object detection](https://www.ultralytics.com/glossary/object-detection) and segmentation tasks. Here's a comparison:
|
||||
|
||||
| Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
|
||||
| ---------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
|
||||
| [Meta SAM-b](sam.md) | 375 | 93.7 | 161440 |
|
||||
| Meta SAM2-b | 162 | 80.8 | 121923 |
|
||||
| Meta SAM2-t | 78.1 | 38.9 | 85155 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 98543 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 backbone | 23.7 | 11.8 | 140 |
|
||||
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **79.5** (1071x faster) |
|
||||
|
||||
For more details, see the [SAM 2 comparison vs YOLOv8](#sam-2-comparison-vs-yolov8) section.
|
||||
SAM 2 models, such as Meta's SAM2-t and SAM2-b, offer powerful zero-shot segmentation capabilities but are significantly larger and slower compared to YOLO11 models. For instance, YOLO11n-seg is approximately **13 times smaller** and over **860 times faster** than SAM2-b. While SAM 2 excels in versatile, prompt-based, and zero-shot segmentation scenarios, YOLO11 is optimized for speed, efficiency, and real-time applications, making it better suited for deployment in resource-constrained environments.
|
||||
|
|
|
|||
|
|
@ -153,20 +153,21 @@ The Segment Anything Model can be employed for a multitude of downstream tasks t
|
|||
|
||||
- More additional args for `Segment everything` see [`Predictor/generate` Reference](../reference/models/sam/predict.md).
|
||||
|
||||
## SAM comparison vs YOLOv8
|
||||
## SAM Comparison vs YOLO
|
||||
|
||||
Here we compare Meta's smallest SAM model, SAM-b, with Ultralytics smallest segmentation model, [YOLOv8n-seg](../tasks/segment.md):
|
||||
Here we compare Meta's SAM-b model with Ultralytics smallest segmentation model, [YOLO11n-seg](../tasks/segment.md):
|
||||
|
||||
| Model | Size<br><sup>(MB)</sup> | Parameters<br><sup>(M)</sup> | Speed (CPU)<br><sup>(ms/im)</sup> |
|
||||
| ---------------------------------------------------------------------------------------------- | ----------------------- | ---------------------------- | --------------------------------- |
|
||||
| Meta SAM-b | 358 | 94.7 | 51096 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 46122 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 [backbone](https://www.ultralytics.com/glossary/backbone) | 23.7 | 11.8 | 115 |
|
||||
| Ultralytics [YOLOv8n-seg](../tasks/segment.md) | **6.7** (53.4x smaller) | **3.4** (27.9x less) | **59** (866x faster) |
|
||||
| [Meta SAM-b](sam.md) | 375 | 93.7 | 49401 |
|
||||
| [MobileSAM](mobile-sam.md) | 40.7 | 10.1 | 25381 |
|
||||
| [FastSAM-s](fast-sam.md) with YOLOv8 [backbone](https://www.ultralytics.com/glossary/backbone) | 23.7 | 11.8 | 55.9 |
|
||||
| Ultralytics [YOLOv8n-seg](yolov8.md) | **6.7** (11.7x smaller) | **3.4** (11.4x less) | **24.5** (1061x faster) |
|
||||
| Ultralytics [YOLO11n-seg](yolo11.md) | **5.9** (13.2x smaller) | **2.9** (13.4x less) | **30.1** (864x faster) |
|
||||
|
||||
This comparison shows the order-of-magnitude differences in the model sizes and speeds between models. Whereas SAM presents unique capabilities for automatic segmenting, it is not a direct competitor to YOLOv8 segment models, which are smaller, faster and more efficient.
|
||||
This comparison demonstrates the substantial differences in model sizes and speeds between SAM variants and YOLO segmentation models. While SAM provides unique automatic segmentation capabilities, YOLO models, particularly YOLOv8n-seg and YOLO11n-seg, are significantly smaller, faster, and more computationally efficient.
|
||||
|
||||
Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test:
|
||||
Tests run on a 2025 Apple M4 Pro Macbook with 24GB of RAM using `torch==2.6.0` and `ultralytics==8.3.90`. To reproduce this test:
|
||||
|
||||
!!! example
|
||||
|
||||
|
|
@ -175,8 +176,8 @@ Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test:
|
|||
```python
|
||||
from ultralytics import ASSETS, SAM, YOLO, FastSAM
|
||||
|
||||
# Profile SAM-b, MobileSAM
|
||||
for file in ["sam_b.pt", "mobile_sam.pt"]:
|
||||
# Profile SAM2-t, SAM2-b, SAM-b, MobileSAM
|
||||
for file in ["sam_b.pt", "sam2_b.pt", "sam2_t.pt", "mobile_sam.pt"]:
|
||||
model = SAM(file)
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
|
|
@ -186,10 +187,11 @@ Tests run on a 2023 Apple M2 Macbook with 16GB of RAM. To reproduce this test:
|
|||
model.info()
|
||||
model(ASSETS)
|
||||
|
||||
# Profile YOLOv8n-seg
|
||||
model = YOLO("yolov8n-seg.pt")
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
# Profile YOLO models
|
||||
for file_name in ["yolov8n-seg.pt", "yolo11n-seg.pt"]:
|
||||
model = YOLO(file_name)
|
||||
model.info()
|
||||
model(ASSETS)
|
||||
```
|
||||
|
||||
## Auto-Annotation: A Quick Path to Segmentation Datasets
|
||||
|
|
@ -277,9 +279,9 @@ yolo predict model=sam_b.pt source=path/to/image.jpg
|
|||
|
||||
For more detailed usage instructions, visit the [Segmentation section](#sam-prediction-example).
|
||||
|
||||
### How do SAM and YOLOv8 compare in terms of performance?
|
||||
### How do SAM and YOLO models compare in terms of performance?
|
||||
|
||||
Compared to YOLOv8, SAM models like SAM-b and FastSAM-s are larger and slower but offer unique capabilities for automatic segmentation. For instance, Ultralytics [YOLOv8n-seg](../tasks/segment.md) is 53.4 times smaller and 866 times faster than SAM-b. However, SAM's zero-shot performance makes it highly flexible and efficient in diverse, untrained tasks. Learn more about performance comparisons between SAM and YOLOv8 [here](#sam-comparison-vs-yolov8).
|
||||
Compared to YOLO models, SAM variants like SAM-b, SAM2-t, MobileSAM, and FastSAM-s are typically larger and slower but offer unique zero-shot segmentation capabilities. For example, Ultralytics [YOLOv8n-seg](../tasks/segment.md) is **11.7x smaller** and **1069x faster** than Meta's original SAM-b model, highlighting YOLO's significant advantage in speed and efficiency. Similarly, the newer [YOLO11n-seg](../tasks/segment.md) provides even smaller size and maintains impressive inference speed. This makes YOLO models ideal for applications requiring rapid, lightweight, and computationally efficient segmentation, while SAM models excel in flexible, promptable, and zero-shot segmentation tasks.
|
||||
|
||||
### How can I auto-annotate my dataset using SAM?
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue