# Promoting Segment Anything Model towards Highly Accurate Dichotomous Image Segmentation

arXiv: https://arxiv.org/abs/2401.00248 · HTML: https://mlsanity.com/paper/2401.00248/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 30 Dec 2023.

## Builds on (most cited first, 12 of 12)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation](https://mlsanity.com/paper/1907.12347/) (2019)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Neural Photo Editing with Introspective Adversarial Networks](https://mlsanity.com/paper/1609.07093/) (2016)
- [Towards High-Resolution Salient Object Detection](https://mlsanity.com/paper/1908.07274/) (2019)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)
- [Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation](https://mlsanity.com/paper/2307.14052/) (2023)

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

- [Effectiveness Assessment of Recent Large Vision-Language Models](https://mlsanity.com/paper/2403.04306/) (2024)
- [S3OD: Towards Generalizable Salient Object Detection with Synthetic Data](https://mlsanity.com/paper/2510.21605/) (2025)
- [Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models](https://mlsanity.com/paper/2410.04884/) (2024)
- [Segment and Matte Anything in a Unified Model](https://mlsanity.com/paper/2601.12147/) (2026)

## Abstract (arXiv)

The Segment Anything Model (SAM) represents a significant breakthrough into foundation models for computer vision, providing a large-scale image segmentation model. However, despite SAM's zero-shot performance, its segmentation masks lack fine-grained details, particularly in accurately delineating object boundaries. Therefore, it is both interesting and valuable to explore whether SAM can be improved towards highly accurate object segmentation, which is known as the dichotomous image segmentation (DIS) task. To address this issue, we propose DIS-SAM, which advances SAM towards DIS with extremely accurate details. DIS-SAM is a framework specifically tailored for highly accurate segmentation, maintaining SAM's promptable design. DIS-SAM employs a two-stage approach, integrating SAM with a modified advanced network that was previously designed to handle the prompt-free DIS task. To better train DIS-SAM, we employ a ground truth enrichment strategy by modifying original mask annotations. Despite its simplicity, DIS-SAM significantly advances the SAM, HQ-SAM, and Pi-SAM ~by 8.5%, ~6.9%, and ~3.7% maximum F-measure. Our code at https://github.com/Tennine2077/DIS-SAM