# BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation

arXiv: https://arxiv.org/abs/2501.06230 · HTML: https://mlsanity.com/paper/2501.06230/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 21 of 21)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Structure-measure: A New Way to Evaluate Foreground Maps](https://mlsanity.com/paper/1708.00786/) (2017)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks](https://mlsanity.com/paper/2003.05128/) (2020)
- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)
- [One-Prompt to Segment All Medical Images](https://mlsanity.com/paper/2305.10300/) (2023)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [Few-shot Medical Image Segmentation with Cycle-resemblance Attention](https://mlsanity.com/paper/2212.03967/) (2022)
- [Multi-view Aggregation Network for Dichotomous Image Segmentation](https://mlsanity.com/paper/2404.07445/) (2024)
- [Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations](https://mlsanity.com/paper/1906.11031/) (2019)
- [MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling](https://mlsanity.com/paper/2303.09373/) (2023)
- [TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars](https://mlsanity.com/paper/2307.10705/) (2023)
- [High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity](https://mlsanity.com/paper/2410.10105/) (2024)
- [BER: Balanced Error Rate For Speaker Diarization](https://mlsanity.com/paper/2211.04304/) (2022)

## Built on by (most cited first, 7 of 7)

- [See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting](https://mlsanity.com/paper/2510.26796/) (2025)
- [Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off](https://mlsanity.com/paper/2508.04825/) (2025)
- [Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning](https://mlsanity.com/paper/2511.19343/) (2025)
- [TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement](https://mlsanity.com/paper/2510.16332/) (2025)
- [Using Gaussian Splats to Create High-Fidelity Facial Geometry and Texture](https://mlsanity.com/paper/2512.16397/) (2025)
- [Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face](https://mlsanity.com/paper/2602.16569/) (2026)
- [CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation](https://mlsanity.com/paper/2607.09362/) (2026)

## Abstract (arXiv)

Current approaches to dichotomous image segmentation (DIS) treat image matting and object segmentation as fundamentally different tasks. As improvements in image segmentation become increasingly challenging to achieve, combining image matting and grayscale segmentation techniques offers promising new directions for architectural innovation. Inspired by the possibility of aligning these two model tasks, we propose a new architectural approach for DIS called Confidence-Guided Matting (CGM). We created the first CGM model called Background Erase Network (BEN). BEN consists of two components: BEN Base for initial segmentation and BEN Refiner for confidence-based refinement. Our approach achieves substantial improvements over current state-of-the-art methods on the DIS5K validation dataset, demonstrating that matting-based refinement can significantly enhance segmentation quality. This work introduces a new paradigm for integrating matting and segmentation techniques, improving fine-grained object boundary prediction in computer vision.