# SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting

arXiv: https://arxiv.org/abs/2607.29033 · HTML: https://mlsanity.com/paper/2607.29033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 56 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 30 of 43)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [TransBTS: Multimodal Brain Tumor Segmentation Using Transformer](https://mlsanity.com/paper/2103.04430/) (2021)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning](https://mlsanity.com/paper/2309.05444/) (2023)
- [MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts](https://mlsanity.com/paper/2404.15159/) (2024)

## Abstract (arXiv)

Existing methods for adapting 2D foundation models such as SAM to 3D volumes either process slices independently---ignoring inter-slice context---or require substantial architectural changes and retraining. In this paper, we present SAM+D, a parameter-efficient framework that lifts SAM-family models by one spatial dimension---enabling 3D volumetric segmentation from 2D SAM and, for the first time via parameter-efficient fine-tuning, end-to-end 4D (3D+T) spatiotemporal segmentation from video-based SAM2---while keeping the vast majority of pre-trained parameters frozen. SAM+D introduces two lightweight, model-agnostic modules into frozen transformer blocks: (1)~Depth-Routed LoRA (DRLoRA) experts with learned routing for spatially adaptive low-rank updates, and (2)~Depth Shift Modules (DSM) for cross-slice feature exchange at zero additional parameter cost. Together, they provide volume-level context while tuning only ~2.8% of parameters for SAM and ~3.7% for SAM2. We evaluate SAM+D in two distinct settings, each lifting the base model by one spatial dimension: 3D segmentation, where SAM(2D,→,3D) is evaluated on four CT benchmarks (KiTS, Pancreas, LiTS, Colon), and 4D segmentation, where SAM2 (2D+T,→,3D+T) is evaluated on a cell tracking challenge (CTC) dataset (Fluo-N3DH-SIM+). In both settings SAM+D achieves competitive or superior results under the single-point prompt setting while using fewer trainable parameters than existing methods, demonstrating that SAM+D generalizes across SAM-family architectures, target dimensionalities (3D, 4D), and domains spanning medical imaging and bio-scene understanding. Code is publicly available at https://github.com/JerrySongCST/SAM-Plus-D.