# From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation

arXiv: https://arxiv.org/abs/2606.23486 · HTML: https://mlsanity.com/paper/2606.23486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 30 of 32)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Real-time Scene Text Detection with Differentiable Binarization](https://mlsanity.com/paper/1911.08947/) (2019)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [CARAFE: Content-Aware ReAssembly of FEatures](https://mlsanity.com/paper/1905.02188/) (2019)
- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion](https://mlsanity.com/paper/2202.10304/) (2022)
- [Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation](https://mlsanity.com/paper/2307.08388/) (2023)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [Learning to Upsample by Learning to Sample](https://mlsanity.com/paper/2308.15085/) (2023)
- [CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging](https://mlsanity.com/paper/2010.07486/) (2020)
- [AnyUp: Universal Feature Upsampling](https://mlsanity.com/paper/2510.12764/) (2025)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [JAFAR: Jack up Any Feature at Any Resolution](https://mlsanity.com/paper/2506.11136/) (2025)
- [Binarized Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2406.05723/) (2024)
- [Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models](https://mlsanity.com/paper/1801.00880/) (2018)
- [DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation](https://mlsanity.com/paper/2205.11115/) (2022)
- [BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution](https://mlsanity.com/paper/2502.00333/) (2025)
- [Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets](https://mlsanity.com/paper/2407.08209/) (2024)
- [CrossDiff: Diffusion Probabilistic Model With Cross-conditional Encoder-Decoder for Crack Segmentation](https://mlsanity.com/paper/2501.12860/) (2025)
- [VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel](https://mlsanity.com/paper/2511.00981/) (2025)
- [Retinal Vessel Segmentation with Deep Graph and Capsule Reasoning](https://mlsanity.com/paper/2409.11508/) (2024)
- [CAPE: Connectivity-Aware Path Enforcement Loss for Curvilinear Structure Delineation](https://mlsanity.com/paper/2504.00753/) (2025)

## Abstract (arXiv)

Curvilinear object segmentation, including vessels and cracks, is challenging due to extreme spatial sparsity and topological fragility, where small local errors can cause severe structural disconnections. Meanwhile, modern segmentation pipelines increasingly rely on strong but hard-to-modify foundation encoders whose heavy downsampling limits fine structural recovery. Motivated by this, we focus on the post-encoder stage and study two recurring and actionable failure modes: a reconstruction bottleneck in high-resolution feature restoration and a decision bottleneck in binarization. We present PEPA, a lightweight Post-Encoder Plug-in Adapter for 2D curvilinear segmentation pipelines with accessible decoder/head features and target, query, or class descriptors. PEPA couples (i) Target-Conditioned Snake Upsampling (TCSU), which uses target-conditioned continuous snake-like sampling to better recover thin and tortuous structures during upsampling, and (ii) Target-Adaptive Differentiable Thresholding (TADT), which predicts target-specific thresholds and optimizes a soft-threshold surrogate with explicit safeguards against trivial bias shifting. Under this post-encoder interface, PEPA can be attached to both prompt-based decoders and conventional dense predictors. Experiments on five medical and industrial benchmarks show that adding PEPA to frozen-encoder baselines yields consistent improvements, with gains in topological connectivity (clDice) typically exceeding those in region overlap (IoU), indicating improved structural continuity. With only ~0.26M additional parameters, PEPA offers a practical post-encoder enhancement for structure-centric segmentation.