# SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization

arXiv: https://arxiv.org/abs/2501.08504 · HTML: https://mlsanity.com/paper/2501.08504/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2025.

## Built on by (most cited first, 3 of 3)

- [AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization](https://mlsanity.com/paper/2503.03088/) (2025)
- [ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization](https://mlsanity.com/paper/2509.05584/) (2025)
- [Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2](https://mlsanity.com/paper/2607.19811/) (2026)

## Abstract (arXiv)

Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures. In contrast to traditional NAS methods, recently proposed one-shot NAS methods prove to be more efficient in performing NAS. One-shot NAS works by generating a singular weight-sharing supernetwork that acts as a search space (container) of subnetworks. Despite its achievements, designing the one-shot search space remains a major challenge. In this work we propose a search space design strategy for Vision Transformer (ViT)-based architectures. In particular, we convert the Segment Anything Model (SAM) into a weight-sharing supernetwork called SuperSAM. Our approach involves automating the search space design via layer-wise structured pruning and parameter prioritization. While the structured pruning applies probabilistic removal of certain transformer layers, parameter prioritization performs weight reordering and slicing of MLP-blocks in the remaining layers. We train supernetworks on several datasets using the sandwich rule. For deployment, we enhance subnetwork discovery by utilizing a program autotuner to identify efficient subnetworks within the search space. The resulting subnetworks are 30-70% smaller in size compared to the original pre-trained SAM ViT-B, yet outperform the pretrained model. Our work introduces a new and effective method for ViT NAS search-space design.