mlsanityData to 14 Oct 2026

SAM3-UNet: Simplified Adaptation of Segment Anything Model 3

arXiv 2512.01789 ↗First posted 1 Dec 2025cs.CVcited by 4

Not on the map. Why?

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.

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

17 of 28 references.

References · 17

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2023Segment Anythingcited by 8,234
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  6. 2025SAM 3: Segment Anything with Conceptscited by 906
  7. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  8. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
  9. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  10. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 290
  11. 2014The Secrets of Salient Object Segmentationcited by 200
  12. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
5 more
  1. 2021Salient Object Detection via Integrity Learningcited by 133
  2. 2020EDN: Salient Object Detection via Extremely-Downsampled Networkcited by 64
  3. 2024SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentationcited by 64
  4. 2022Efficient Mirror Detection via Multi-level Heterogeneous Learningcited by 13
  5. 2025Uncertainty Guided Refinement for Fine-Grained Salient Object Detectioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentationcited by 1
  2. 2026Surgical Anatomy Recognition with Context Learning using Foundation Representationscited by 1
  3. 2026When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentationcited by 0
  4. 2026CoRe-SAM3: Conditional Semantic--Visual Reconciliation for SAM3 Crack Segmentationcited by 0