Update README.md
Browse files
README.md
CHANGED
|
@@ -5,5 +5,6 @@ license: apache-2.0
|
|
| 5 |
> [Zigeng Chen](https://github.com/czg1225), [Gongfan Fang](https://fangggf.github.io/), [Xinyin Ma](https://horseee.github.io/), [Xinchao Wang](https://sites.google.com/site/sitexinchaowang/)
|
| 6 |
> [Learning and Vision Lab](http://lv-nus.org/), National University of Singapore
|
| 7 |
> Paper: [[Arxiv]](https://arxiv.org/abs/2312.05284)
|
|
|
|
| 8 |
>
|
| 9 |
> **SlimSAM** is a novel SAM compression method, which efficiently reuses pre-trained SAMs without the necessity for extensive retraining. This is achieved by the efficient reuse of pre-trained SAMs through a unified pruning-distillation framework. To enhance knowledge inheritance from the original SAM, we employ an innovative alternate slimming strategy that partitions the compression process into a progressive procedure. Diverging from prior pruning techniques, we meticulously prune and distill decoupled model structures in an alternating fashion. Furthermore, a novel label-free pruning criterion is also proposed to align the pruning objective with the optimization target, thereby boosting the post-distillation after pruning. SlimSAM achieves approaching performance while reducing the parameter counts to **0.9\% (5.7M)**, MACs to **0.8\% (21G)**, and requiring mere **0.1\% (10k)** of the training data when compared to the original SAM-H. Extensive experiments demonstrate that our method realize significant superior performance while utilizing over **10 times** less training data when compared to other SAM compression methods.
|
|
|
|
| 5 |
> [Zigeng Chen](https://github.com/czg1225), [Gongfan Fang](https://fangggf.github.io/), [Xinyin Ma](https://horseee.github.io/), [Xinchao Wang](https://sites.google.com/site/sitexinchaowang/)
|
| 6 |
> [Learning and Vision Lab](http://lv-nus.org/), National University of Singapore
|
| 7 |
> Paper: [[Arxiv]](https://arxiv.org/abs/2312.05284)
|
| 8 |
+
> GitHub: [[SlimSAM]](https://github.com/czg1225/SlimSAM)
|
| 9 |
>
|
| 10 |
> **SlimSAM** is a novel SAM compression method, which efficiently reuses pre-trained SAMs without the necessity for extensive retraining. This is achieved by the efficient reuse of pre-trained SAMs through a unified pruning-distillation framework. To enhance knowledge inheritance from the original SAM, we employ an innovative alternate slimming strategy that partitions the compression process into a progressive procedure. Diverging from prior pruning techniques, we meticulously prune and distill decoupled model structures in an alternating fashion. Furthermore, a novel label-free pruning criterion is also proposed to align the pruning objective with the optimization target, thereby boosting the post-distillation after pruning. SlimSAM achieves approaching performance while reducing the parameter counts to **0.9\% (5.7M)**, MACs to **0.8\% (21G)**, and requiring mere **0.1\% (10k)** of the training data when compared to the original SAM-H. Extensive experiments demonstrate that our method realize significant superior performance while utilizing over **10 times** less training data when compared to other SAM compression methods.
|