YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling

• URL: http://arxiv.org/abs/2608.15713v2
• Date: Tue, 18 Aug 2026 06:01:33 GMT
• Title: YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling
• Abstract summary: This paper tests the premise that a stride-4 level would claim 75.3% of anchors, and complete misses rather than localisation errors dominate baseline failures.<n>Fifteen models were trained from scratch under one recipe, five scales each of YOLO26-RD and of matched YOLO26 and YOLOv12 families.<n>YOLO26-RD-l is the best of the fifteen at 0.809 mAP50 and 0.497 mAP50-95, improving on the YOLO26 reference by 0.031 and 0.030 and leading all six per class entries.
• Score: 2.274915755738124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pavement distress detectors are conventionally specialised for small objects, typically by adding a stride-4 detection head and replacing strided convolution with space-to-depth downsampling. This paper tests that premise against the annotation geometry of region level survey imagery and finds it fails: 1.28% of instances are small at 640 resolution while 70.37% are large, yet a stride-4 level would claim 75.3% of anchors, and complete misses rather than localisation errors dominate baseline failures. YOLO26-RD therefore reallocates the anchor budget, retaining the stride-4 branch as neck features but carrying no detection level there, and adds LearnableContrast, a 494 parameter per tile correction learned from the detection loss and active at inference, and EdgeSPD, a lossless space-to-depth downsampler gated by a fixed Sobel prior. Fifteen models were trained from scratch under one recipe, five scales each of YOLO26-RD and of matched YOLO26 and YOLOv12 families. Averaged over scales YOLO26-RD returns 0.790 mAP50 and 0.482 mAP50-95 against 0.776 and 0.471 for YOLO26 and 0.755 and 0.468 for YOLOv12; it exceeds both on mAP50 at every scale from s upward, and at m, l and x it leads on both metrics, twelve pairwise comparisons decided without exception. YOLO26-RD-l is the best of the fifteen at 0.809 mAP50 and 0.497 mAP50-95, improving on the YOLO26 reference by 0.031 and 0.030 and leading all six per class entries; every arm of a module ablation also exceeds that reference. The margin is thus a property of the architecture rather than of one tuned configuration, though three of the twelve margins lie inside the dataset 0.015 resolution limit and the held out split reproduces the ordering against YOLO26 but not YOLOv12 at scale x. As a TensorRT FP16 engine the released model sustains 98 frames per second on an entry level accelerator, against the 21 needed at 100 km/h.

Related papers

• Depth-Aware Pothole Detection Using YOLO and RT-DETR at the Edge [0.0]
  Existing approaches depend on 2D RGB images and cannot measure physical depth of potholes.<n>We present a depthaware pothole detection framework and then compare five architectures.<n>YOLOv8n, YOLOv8nSeg, YOLOv9t, RTDETRL, and RTDETRX for RGB-D sensor fusion-based detection and automated depth measurement.
  arXiv  Detail & Related papers  (2026-08-27T19:18:08Z)
• Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation [0.9530026127073782]
  In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design.<n>Our Volume-Conditioned Adaptive Post-Processing scheme adjusts component-size thresholds to each case's predicted lesion burden.<n>A resolution-aware attention architecture (Viola2Plus) designed for small-lesion segmentation shows why the distinction matters.
  arXiv  Detail & Related papers  (2026-08-17T10:30:51Z)
• YOLO-PEFT: Parameter-Efficient Fine-Tuning on YOLO Family [35.54329849535432]
  YOLO-PEFT is a structure-aware framework that formulates adapter placement as an auditable constraint-planning problem.<n>Within the evaluated detector families, YOLO-PEFT replaces manual target-module trial and error with explicit, inspectable planning.
  arXiv  Detail & Related papers  (2026-08-07T09:59:19Z)
• Rough Path Signature-Guided Geometry Augmentation for Few-Shot Industrial Surface Defect Detection [0.0]
  This paper proposes rough path signature-guided geometry augmentation (RPS-GA)<n>RPS-GA is a geometry-aware approach in which Canny edge contours are treated as ordered planar paths.<n>Results indicate that second-order path-signature geometry offers a practical way to strengthen few-shot industrial defect detection.
  arXiv  Detail & Related papers  (2026-07-14T01:14:58Z)
• Real-Time Source-Free Object Detection [40.10658212485104]
  Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints.<n>We show that building on YOLOv10, an NMS-free dual-head detector, we achieve state-of-the-art adaptation accuracy while being faster and more compact.
  arXiv  Detail & Related papers  (2026-06-30T15:38:56Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness [45.148328075418156]
  A deployed ordering agent is decomposed into a fixed taxonomy of layers.<n>The pure suite runs in CI on every change against a locked per-slice baseline.<n>We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers.
  arXiv  Detail & Related papers  (2026-06-10T05:55:13Z)
• YOLO26-RipeLoc Lite: A lightweight architecture for tomato ripeness detection and picking point localization in greenhouse robotic harvesting [1.5466093929120728]
  This paper proposes YOLO26-RipeLoc Lite for simultaneous detection, ripeness classification, and center-point localization of greenhouse tomatoes.<n>YOLO26-RipeLoc Lite achieves mAP@0.5 of 92.9% (95.2% ripe, 90.6% unripe) with the highest precision (95.2%) among all evaluated architectures.
  arXiv  Detail & Related papers  (2026-05-26T15:00:24Z)
• Pixel-Level Pavement Distress Assessment Using Instance Segmentation [0.0]
  This paper presents a vision-based pavement distress analysis system based on Mask R-CNN instance segmentation.<n>The best-performing model achieved 84.23% precision, 90.04% recall, and an F1 score of 87.04% under the project-specific bounding-box matching protocol.<n>The results show that instance segmentation is a practical direction for field pavement imagery and aggregate crack-area estimation.
  arXiv  Detail & Related papers  (2026-05-25T17:53:23Z)
• From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection [2.2908242575265025]
  High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs.<n>We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets.
  arXiv  Detail & Related papers  (2026-05-23T20:40:33Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Paired-CSLiDAR: Height-Stratified Registration for Cross-Source Aerial-Ground LiDAR Pose Refinement [46.13526676100776]
  We introduce Paired-CSLiDAR, a cross-source aerial-ground LiDAR benchmark for single-scan pose refinement.<n>The benchmark contains 12,683 ground-aerial pairs across 6 evaluation sites.<n>We propose Residual-Guided Stratified Registration (RGSR), a training-free, geometry-only refinement pipeline.
  arXiv  Detail & Related papers  (2026-05-01T13:14:20Z)
• Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs [2.111646739533638]
  Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility.<n>We propose a lightweight 'Online Architecture' strategy by strategically inserting Global Average Pooling layers at various network depths.<n>This strategy achieves a massive 98% reduction in trainable parameters (from 5.2M to just 82K) and a 90% reduction in total network size.
  arXiv  Detail & Related papers  (2026-04-30T13:52:42Z)
• DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery [0.0]
  DroneScan-YOLO is a holistic system contribution that addresses limitations through four coordinated design choices.<n>DroneScan-YOLO achieves 55.3% mAP@50 and 35.6% mAP@50-95, outperforming the YOLOv8s baseline by +16.6 and +12.3 points respectively.
  arXiv  Detail & Related papers  (2026-04-14T20:14:57Z)
• YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection [0.0]
  Road damage detection is a critical task for ensuring traffic safety and maintaining infrastructure integrity.<n>This paper proposes a high-precision and lightweight model, YOLO - Road Orthogonal Compact (YOLO-ROC)
  arXiv  Detail & Related papers  (2025-07-31T03:35:19Z)
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception [58.06752127687312]
  We propose YOLOv13, an accurate and lightweight object detector.<n>We propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism.<n>We also propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm.
  arXiv  Detail & Related papers  (2025-06-21T15:15:03Z)
• YOLOv12: Attention-Centric Real-Time Object Detectors [38.507511985479006]
  This paper proposes an attention-centric YOLO framework, YOLOv12, that matches the speed of previous CNN-based ones.<n>YOLOv12 surpasses all popular real-time object detectors in accuracy with competitive speed.
  arXiv  Detail & Related papers  (2025-02-18T04:20:14Z)
• Automating global landslide detection with heterogeneous ensemble deep-learning classification [44.99833362998488]
  Landslides threaten infrastructure, including roads, railways, buildings, and human life. Hazard-based spatial planning and early warning systems are cost-effective strategies to reduce the risk to society from landslides. Deep learning models have recently been applied for landside mapping using medium- to high-resolution satellite images as input.
  arXiv  Detail & Related papers  (2023-09-12T10:56:16Z)
• Detection Transformer with Stable Matching [48.963171068785435]
  We show that the most important design is to use and only use positional metrics to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR's classification loss and matching cost. We achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 12 epochs and 24 epochs training settings.
  arXiv  Detail & Related papers  (2023-04-10T17:55:37Z)
• CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs [41.43273142203345]
  We harness the flexibility of FPGAs to develop a novel object detection pipeline with deformable convolutions. With our high-efficiency implementation, our solution reaches 26.9 frames per second with a tiny model size of 0.76 MB. Our model gets to 67.1 AP50 on Pascal VOC with only 2.9 MB of parameters-20.9x smaller but 10% more accurate than Tiny-YOLO.
  arXiv  Detail & Related papers  (2020-06-12T17:56:47Z)

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.