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

• URL: http://arxiv.org/abs/2606.23486v1
• Date: Mon, 22 Jun 2026 15:33:06 GMT
• Title: From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation
• Abstract summary: We present PEPA, a lightweight Post-Encoder Plug-in Adapter for 2D curvilinear segmentation pipelines.<n> PEPA couples (i) Target-Conditioned Snake Upsampling (TCSU), which uses target-conditioned continuous snake-like sampling to better recover thin and tortuous structures.<n>Experiments on five medical and industrial benchmarks show that adding PEPA to frozen-encoder baselines yields consistent improvements.
• Score: 21.002642702889364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 $\sim$0.26M additional parameters, PEPA offers a practical post-encoder enhancement for structure-centric segmentation.

Related papers

• Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA [19.22449941750196]
  We propose a manifold-aware framework designed to disentangle perceptual distortions from dominant semantics.<n>Our approach significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-09-15T05:38:56Z)
• Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator Learning [0.21847754147782886]
  Two-Scale Localized PCA-Net decomposes the solution into a coarse-global component and local residual corrections.<n>It substantially reduces reconstruction error and visible block artifacts relative to plain and overlap-based localized PCA-Net.
  arXiv  Detail & Related papers  (2026-09-07T22:36:24Z)
• HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction [8.146414118644069]
  We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC)<n>Despite the strong performance of DeepSeek-V4's native Multi-Token Prediction (MTP) module on initial token drafting, its draft accuracy degrades sharply at later positions.<n>Although the original DFlash method supports efficient one-pass block drafting, it cannot be seamlessly adapted to the HC paradigm.
  arXiv  Detail & Related papers  (2026-06-25T08:31:53Z)
• DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction [8.972672149050627]
  Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems.<n>This task presents a modeling challenge: click signals are abundant and exhibit short temporal horizons, whereas conversion signals are inherently sparse, long-delayed, and frequently unattributed.<n>We propose DUET, a framework that explicitly partitions user behavioral data into two domain-coherent streams -- clicks and conversions.
  arXiv  Detail & Related papers  (2026-06-08T23:13:58Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Adaptive Data Compression and Reconstruction for Memory-Bounded EEG Continual Learning [0.0]
  We propose Adaptive Data Compression and Reconstruction (ADaCoRe) for Unsupervised Individual Continual Learning (UICL)<n>ADaCoRe is a memory-efficient pipeline composed of saliency-driven personalization protection, rational polyphase compression, adjoint reconstruction with verbatim on protected indices, and prototype-confidence selection for adaptive exemplar maintenance.
  arXiv  Detail & Related papers  (2026-05-04T18:59:35Z)
• Towards Practical Lossless Neural Compression for LiDAR Point Clouds [84.36825469211375]
  extreme sparsity of high-precision geometric details hinders efficient context modeling.<n>Our framework comprises two lightweight modules.<n>Experiments demonstrate competitive compression performance at real-time speed.
  arXiv  Detail & Related papers  (2026-03-26T10:02:07Z)
• VSCOUT: A Hybrid Variational Autoencoder Approach to Outlier Detection in High-Dimensional Retrospective Monitoring [0.0]
  VSCOUT is a distribution-free framework designed for retrospective (Phase I) monitoring in high-dimensional settings.<n>VSCOUT achieves superior sensitivity to special-cause structure while maintaining controlled false alarms.<n>Its scalability, distributional flexibility, and resilience position VSCOUT as a practical and effective method for retrospective modeling and anomaly detection in AI-enabled environments.
  arXiv  Detail & Related papers  (2026-01-28T18:30:48Z)
• Learning Binary Autoencoder-Based Codes with Progressive Training [1.8620637029128544]
  Autoencoder (AE) based approaches have gained attention for the end-to-end design of communication systems.<n>These results indicate that compact AE architectures can effectively learn structured, algebraically optimal binary codes through stable and straightforward training.
  arXiv  Detail & Related papers  (2025-11-12T11:32:03Z)
• Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series [2.5895291094206825]
  This paper introduces a novel architecture that integrates a self-supervised, Transformer-based Change Point Detection (CPD) module into the Option-Critic framework.<n>The CPD module is trained using pseudo-labels derived from intrinsic signals to infer latent shifts in environment dynamics without external supervision.<n>Experiments on the Four-Rooms and Pinball tasks demonstrate that CPD-guided agents exhibit accelerated convergence, higher cumulative returns, and significantly improved option specialization.
  arXiv  Detail & Related papers  (2025-10-28T21:34:23Z)
• DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds [54.96190721255167]
  Lossy compression relies on an autoencoder to transform a point cloud into latent points for storage.<n>We propose a diffusion-based framework guided by sparse priors that achieves high reconstruction quality, especially at lows.
  arXiv  Detail & Related papers  (2024-11-21T05:41:35Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR [67.63332492134332]
  We design an optimized conformer that is small enough to meet on-device restrictions and has fast inference on TPUs. Our proposed encoder can double as a strong standalone encoder in on device, and as the first part of a high-performance ASR pipeline.
  arXiv  Detail & Related papers  (2023-03-31T23:30:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.