Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling

• URL: http://arxiv.org/abs/2605.31048v1
• Date: Fri, 29 May 2026 09:24:26 GMT
• Title: Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling
• Abstract summary: Cracks have limited category-level semantics but strong morphological regularities, being thin, sparse, anisotropic, locally fragmented, and easily confused with textures or shadows.<n>We propose RIFT, a compact family of morphology-aligned crack segmentation models. Rather than compressing a complex generic architecture, RIFT is simple by design, preserving local evidence, aggregating cooperative directional continuity, and restoring crack structures through lightweight multi-scale fusion.
• Score: 8.944881958991386
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, and auxiliary enhancement branches. Although effective, this raises whether stronger generic feature mixing is the most suitable direction for crack segmentation. We instead formulate crack segmentation as sparse structural recovery. Cracks have limited category-level semantics but strong morphological regularities, being thin, sparse, anisotropic, locally fragmented, and easily confused with textures or shadows. Thus, the key bottleneck lies in preserving weak structural evidence, recovering directional continuity, and suppressing background coupling. We propose RIFT, a compact family of morphology-aligned crack segmentation models. Rather than compressing a complex generic architecture, RIFT is simple by design, preserving local evidence, aggregating cooperative directional continuity, and restoring crack structures through lightweight multi-scale fusion. Experiments on four public benchmarks show that RIFT achieves the best or tied-best results across the 16 main metrics against reproduced representative baselines. RIFT-B gives the strongest overall accuracy, while RIFT-T provides the best deployment efficiency with only 0.47M parameters and high inference speed. Topology-aware evaluation, ablations, transfer experiments, and visualizations further verify that task-aligned simplicity can match or surpass complex hybrid architectures when its inductive bias fits crack morphology. Code: https://github.com/xauat-liushipeng/RIFT

Related papers

• Breaking the Compression Barrier: Cross-Architecture Compression Boundary Learning via Reverse Regrowth [1.454787329315493]
  We propose a boundary-Learning reverse framework, BRIDGE, to reformulate compression as a constructive boundary-search problem.<n>Our method first drives the model to an extremely sparse state to expose the collapse region, and then selectively regenerates the critical structure to restore performance.<n>Experiments show that our method can recover models from the brink of collapse on both CNNs and Transformer architectures.
  arXiv  Detail & Related papers  (2026-08-17T01:59:23Z)
• CurvSegFlow: Time-Conditioned Flow Matching for Robust Segmentation of Curvilinear Structures in Noisy Biomedical Images [33.96173028868693]
  We propose CurvSegFlow, a segmentation framework based on time-conditioned flow matching.<n>The proposed model combines a U-Net backbone with triple-term loss function and temporal embeddings to guide the refinement process.<n>CurvSegFlow is evaluated on multiple synthetic and real microtubule datasets, as well as on public benchmarks of retinal vessels, corneal nerves and coronary arteries.
  arXiv  Detail & Related papers  (2026-06-19T17:12:49Z)
• Universal Image Restoration via Internalized Chain-of-Thought Reasoning [52.763760468548504]
  Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations.<n>Recent works adopt Chain-of-Thought (CoT) reasoning for multi-round restoration using specialized modules.<n>We introduce CoTIR, a universal image restoration framework that internalizes CoT reasoning within a single model.
  arXiv  Detail & Related papers  (2026-06-16T06:01:36Z)
• Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure [6.830580384536778]
  CrackGeoFM is a framework that combines a frozen visual foundation backbone with crack-specific adaptation for mask prediction, skeleton reconstruction, and uncertainty estimation.<n>Across 20 crack datasets, CrackGeoFM achieves state-of-the-art segmentation, improved topology preservation, calibrated uncertainty, and effective few-shot adaptation with only five labeled images.
  arXiv  Detail & Related papers  (2026-06-04T03:08:01Z)
• CrackForward: Context-Aware Severity Stage Crack Synthesis for Data Augmentation [1.6440434996206623]
  We propose a novel context-aware generative framework designed to synthesize realistic crack growth patterns for data augmentation.<n>CrackForward explicitly models crack morphology by combining directional crack elongation with learned thickening and branching.
  arXiv  Detail & Related papers  (2026-04-21T19:36:27Z)
• PRISM: Parallel Residual Iterative Sequence Model [52.26239951489612]
  We propose PRISM (Parallel Residual Iterative Sequence Model) to resolve this tension.<n>PRISM introduces a solver-inspired inductive bias that captures key structural properties of multi-step refinement in a parallelizable form.<n>We prove that this formulation achieves Rank-$L$ accumulation, structurally expanding the update manifold beyond the single-step Rank-$1$ bottleneck.
  arXiv  Detail & Related papers  (2026-02-11T12:39:41Z)
• StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval [75.28673512571449]
  A key challenge in Continual Text-to-Video Retrieval is feature drift.<n>We propose StructAlign, a structured cross-modal alignment method for CTVR.<n>Our method consistently outperforms state-of-the-art continual retrieval approaches.
  arXiv  Detail & Related papers  (2026-01-28T13:34:44Z)
• Unleashing Degradation-Carrying Features in Symmetric U-Net: Simpler and Stronger Baselines for All-in-One Image Restoration [52.82397287366076]
  All-in-one image restoration aims to handle diverse degradations (e.g., noise, blur, adverse weather) within a unified framework.<n>In this work, we reveal a critical insight: well-crafted feature extraction inherently encodes degradation-carrying information.<n>Our symmetric design preserves intrinsic degradation signals robustly, rendering simple additive fusion in skip connections.
  arXiv  Detail & Related papers  (2025-12-11T12:20:31Z)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• Deep Learning-Based Fatigue Cracks Detection in Bridge Girders using Feature Pyramid Networks [8.59780173800845]
  This study proposes a framework of automatic crack segmentation from high-resolution images containing crack information about steel box girders of bridges. Considering the multi-scale feature of cracks, convolutional neural network architecture of Feature Pyramid Networks (FPN) for crack detection is proposed.
  arXiv  Detail & Related papers  (2024-10-28T16:16:15Z)
• CrackSCF: Lightweight Cascaded Fusion Network for Robust and Efficient Structural Crack Segmentation [36.93774494071781]
  CrackSCF is a lightweight Cascaded Fusion Crack Network designed to achieve robust crack segmentation.<n>This approach efficiently captures local patterns while operating with a minimal computational footprint.<n>The experimental results show that the CrackSCF method consistently outperforms the existing methods.
  arXiv  Detail & Related papers  (2024-08-23T03:21:51Z)
• Isomorphic Pruning for Vision Models [56.286064975443026]
  Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. We present Isomorphic Pruning, a simple approach that demonstrates effectiveness across a range of network architectures.
  arXiv  Detail & Related papers  (2024-07-05T16:14:53Z)
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
  A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.<n>We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.<n>We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
  arXiv  Detail & Related papers  (2024-07-02T14:12:21Z)
• Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset [11.282003429161163]
  This paper examines the inherent characteristics of cracks so as to introduce boundary features into crack identification. It builds a boundary guidance crack segmentation model (BGCrack) with targeted structures and modules, including a high frequency module. This paper provides a steel crack dataset that establishes a unified and fair benchmark for the identification of steel cracks.
  arXiv  Detail & Related papers  (2023-06-15T15:25:53Z)

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.