File size: 1,614 Bytes
9a0f6e3 9f6186c ce91e85 9f6186c |
1 2 3 4 5 6 7 8 9 10 11 |
---
license: apache-2.0
---
> **0.1% Data Makes Segment Anything Slim**
> [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/)
> [Learning and Vision Lab](http://lv-nus.org/), National University of Singapore
> Paper: [[Arxiv]](https://arxiv.org/abs/2312.05284)
> GitHub: [[SlimSAM]](https://github.com/czg1225/SlimSAM)
>
> **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.
|