From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection

• URL: http://arxiv.org/abs/2605.24726v1
• Date: Sat, 23 May 2026 20:40:33 GMT
• Title: From Full Boards to Tiny Defects: Scale-Aware Tile Inference with Topology-Aware Merging for High-Resolution PCB Defect Detection
• Abstract summary: 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.
• Score: 2.2908242575265025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-resolution printed circuit board (PCB) inspection suffers from resolution collapse when full-board images are resized to standard detector inputs: micro-scale defects shrink to a few pixels and are missed. Tile-based inference preserves local detail but introduces boundary artefacts at tile edges, causing split detections and false negatives. We present a systematic comparison of five inference strategies evaluated on two high-resolution PCB defect datasets, PCB-Defect (230 images, 1704 annotations) and HRIPCB (693 images, 2 953 annotations), spanning six defect classes. We show that training-inference scale consistency is critical: a detector trained on full images collapses to mAP@50 = 0.01 under tile inference, while the same architecture trained on 640*640 tile crops achieves 0.72 and 0.94 on the two datasets respectively. We further exploited Topology-Aware Tile Merging (TA-TM), a training-free post-processing method that builds a tile-adjacency graph and adjusts boundary-sensitive detection scores using neighbour-tile agreement before global NMS. Across both datasets, adding 128 px tile overlap raises boundary-zone recall from ~26-63% to ~70-100%, TA-TM achieves the best mAP@50 on both benchmarks, and tile inference recovers 46-100% of small defects missed entirely by full-image methods. Results are consistent across datasets, confirming the generalizability of the proposed strategy. TA-TM requires no retraining and is architecture-agnostic, making it directly applicable to existing PCB inspection pipelines.

Related papers

• Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems [48.501415601682815]
  Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.<n>We show that flow map models implicitly define a one- parameter family of denoisers that continuously spans the distortion perception frontier.<n>Within a Plug-and-Play solver, the same mechanism extends to general inverse problems, where it controls a tradeoff between perceptual alignment and data consistency.
  arXiv  Detail & Related papers  (2026-06-18T05:15:43Z)
• Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning [52.41928980786654]
  We propose PathCTM to enable token-efficient scale-space continuous reasoning for gigapixel whole slide images.<n>PathCTM formulates diagnostic inference as a dynamic sequential information pursuit.<n>It reduces the number of required image patches by 95.95% and shortens inference time by approximately 95.62%, while maintaining AUC without degradation.
  arXiv  Detail & Related papers  (2026-05-19T07:46:44Z)
• UniPCB: A Generation-Assisted Detection Framework for PCB Defect Inspection [16.687894734386322]
  We propose a generation-assisted PCB defect inspection framework that integrates controlled defect synthesis with task-specific defect detection.<n>Experiments on DsPCBSD+ demonstrate that UniPCB achieves mAP@0.5 of 98.0% and mAP@0.5:0.95 of 61.8% on defect detection, surpassing all compared methods.
  arXiv  Detail & Related papers  (2026-05-06T08:30:27Z)
• HMS-VesselNet: Hierarchical Multi-Scale Attention Network with Topology-Preserving Loss for Retinal Vessel Segmentation [0.0]
  HMS-VesselNet is a hierarchical multi-scale network that processes fundus images across four parallel branches at different resolutions.<n>Tested on 68 images from DRIVE, STARE, and CHASE_DB1 using 5-fold cross-validation, the model achieves a mean Dice of 88.72 +/- 0.67%, Sensitivity of 90.78 +/- 1.42%, and AUC of 98.25 +/- 0.21%.
  arXiv  Detail & Related papers  (2026-03-23T12:16:45Z)
• Ultrafast Deep Learning-Based Scatter Estimation in Cone-Beam Computed Tomography [7.864992877255044]
  scatter artifacts drastically degrade the image quality of cone-beam computed tomography (CBCT) scans.<n>Deep learning-based methods show promise in estimating scatter from CBCT measurements.<n>Their deployment in mobile CBCT systems or edge devices is still limited due to the large memory footprint of the networks.
  arXiv  Detail & Related papers  (2025-09-10T20:07:56Z)
• AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification [51.525891360380285]
  AHDMIL is an Asymmetric Hierarchical Distillation Multi-Instance Learning framework.<n>It eliminates irrelevant patches through a two-step training process.<n>It consistently outperforms previous state-of-the-art methods in both classification performance and inference speed.
  arXiv  Detail & Related papers  (2025-08-07T07:47:16Z)
• PRISM: Distributed Inference for Foundation Models at Edge [73.54372283220444]
  PRISM is a communication-efficient and compute-aware strategy for distributed Transformer inference on edge devices.<n>We evaluate PRISM on ViT, BERT, and GPT-2 across diverse datasets.
  arXiv  Detail & Related papers  (2025-07-16T11:25:03Z)
• SPFFNet: Strip Perception and Feature Fusion Spatial Pyramid Pooling for Fabric Defect Detection [0.0]
  We propose an improved fabric defect detection model based on YOLOv11.<n>We introduce a Strip Perception Module (SPM) that improves feature capture through multi-scale convolution.<n>We also propose a novel focal enhanced complete intersection over union (FECIoU) metric with adaptive weights.
  arXiv  Detail & Related papers  (2025-02-03T15:33:11Z)
• Unsupervised Fault Detection using SAM with a Moving Window Approach [0.0]
  We present an unsupervised method that uses the high end Segment Anything Model (SAM) and a moving window approach. We aim to overcome these challenges without requiring fine tun ing or labeled data.
  arXiv  Detail & Related papers  (2024-07-08T18:12:29Z)
• Learning to utilize image second-order derivative information for crisp edge detection [16.152236524867078]
  Edge detection is a fundamental task in computer vision.<n>Recent top-performing edge detection methods tend to generate thick and noisy edge lines.<n>We propose a second-order derivative-based multi-scale contextual enhancement module (SDMCM) to help the model locate true edge pixels accurately.<n>We also construct a hybrid focal loss function (HFL) to alleviate the imbalanced distribution issue.<n>In the end, we propose a U-shape network named LUS-Net which is based on the SDMCM and BRM for edge detection.
  arXiv  Detail & Related papers  (2024-06-09T13:25:02Z)
• Decoupled Prototype Learning for Reliable Test-Time Adaptation [50.779896759106784]
  Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
  arXiv  Detail & Related papers  (2024-01-15T03:33:39Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)

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.