# SAM3-UNet: Simplified Adaptation of Segment Anything Model 3

arXiv: https://arxiv.org/abs/2512.01789 · HTML: https://mlsanity.com/paper/2512.01789/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [EDN: Salient Object Detection via Extremely-Downsampled Network](https://mlsanity.com/paper/2012.13093/) (2020)
- [SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation](https://mlsanity.com/paper/2408.08870/) (2024)
- [Efficient Mirror Detection via Multi-level Heterogeneous Learning](https://mlsanity.com/paper/2211.15644/) (2022)
- [Uncertainty Guided Refinement for Fine-Grained Salient Object Detection](https://mlsanity.com/paper/2504.09666/) (2025)

## Built on by (most cited first, 4 of 4)

- [Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation](https://mlsanity.com/paper/2604.07916/) (2026)
- [Surgical Anatomy Recognition with Context Learning using Foundation Representations](https://mlsanity.com/paper/2606.22124/) (2026)
- [When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation](https://mlsanity.com/paper/2607.02708/) (2026)
- [CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentation](https://mlsanity.com/paper/2609.05816/) (2026)

## Abstract (arXiv)

In this paper, we introduce SAM3-UNet, a simplified variant of Segment Anything Model 3 (SAM3), designed to adapt SAM3 for downstream tasks at a low cost. Our SAM3-UNet consists of three components: a SAM3 image encoder, a simple adapter for parameter-efficient fine-tuning, and a lightweight U-Net-style decoder. Preliminary experiments on multiple tasks, such as mirror detection and salient object detection, demonstrate that the proposed SAM3-UNet outperforms the prior SAM2-UNet and other state-of-the-art methods, while requiring less than 6 GB of GPU memory during training with a batch size of 12. The code is publicly available at https://github.com/WZH0120/SAM3-UNet.