LINEA: Fast and Accurate Line Detection Using Scalable Transformers

• URL: http://arxiv.org/abs/2505.16264v1
• Date: Thu, 22 May 2025 05:56:10 GMT
• Title: LINEA: Fast and Accurate Line Detection Using Scalable Transformers
• Authors: Sebastian Janampa, Marios Pattichis,
• Abstract summary: Line detection is a basic digital image processing operation used by higher-level processing methods.<n>Recent transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of significantly lower inference speeds.<n>This paper develops a new transformer-based method that is significantly faster without requiring pretraining the attention mechanism on large datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Line detection is a basic digital image processing operation used by higher-level processing methods. Recently, transformer-based methods for line detection have proven to be more accurate than methods based on CNNs, at the expense of significantly lower inference speeds. As a result, video analysis methods that require low latencies cannot benefit from current transformer-based methods for line detection. In addition, current transformer-based models require pretraining attention mechanisms on large datasets (e.g., COCO or Object360). This paper develops a new transformer-based method that is significantly faster without requiring pretraining the attention mechanism on large datasets. We eliminate the need to pre-train the attention mechanism using a new mechanism, Deformable Line Attention (DLA). We use the term LINEA to refer to our new transformer-based method based on DLA. Extensive experiments show that LINEA is significantly faster and outperforms previous models on sAP in out-of-distribution dataset testing.

Related papers

• Efficient Lines Detection for Robot Soccer [0.0]
  This paper presents a method for detecting soccer field lines using the ELSED algorithm, extended with a classification step that analyzes RGB color transitions to identify lines belonging to the field.<n>Our approach achieves accuracy comparable to a state-of-the-art deep learning model while offering higher processing speed, making it well-suited for real-time applications on low-power robotic platforms.
  arXiv  Detail & Related papers  (2025-07-25T17:54:51Z)
• Improving Transformer Based Line Segment Detection with Matched Predicting and Re-ranking [21.2588921381058]
  RANK-LETR is a novel Transformer-based line segment detection method.<n>We propose a new line segment proposal method, wherein the feature point nearest to the centroid of the line segment directly predicts the location.<n> Experimental results demonstrate that our method outperforms other Transformer-based and CNN-based approaches in prediction accuracy.
  arXiv  Detail & Related papers  (2025-02-25T01:54:40Z)
• Linear Transformers are Versatile In-Context Learners [19.988368693379087]
  We prove that each layer of a linear transformer maintains a weight vector for an implicit linear regression problem. We also investigate the use of linear transformers in a challenging scenario where the training data is corrupted with different levels of noise. Remarkably, we demonstrate that for this problem linear transformers discover an intricate and highly effective optimization algorithm.
  arXiv  Detail & Related papers  (2024-02-21T23:45:57Z)
• Transmission Line Detection Based on Improved Hough Transform [8.243900941694138]
  We introduce an enhanced Hough transform technique tailored for detecting transmission lines in complex backgrounds. We significantly reduce both false positives and missed detections, thereby improving the accuracy of transmission line identification.
  arXiv  Detail & Related papers  (2024-02-05T06:37:09Z)
• Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining [25.669038513039357]
  This paper provides a theoretical framework that analyzes supervised pretraining for in-context reinforcement learning. We show transformers with ReLU attention can efficiently approximate near-optimal online reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2023-10-12T17:55:02Z)
• Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method [51.30748775681917]
  We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
  arXiv  Detail & Related papers  (2022-12-22T09:05:07Z)
• DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients [105.25109274550607]
  Line segments are increasingly used in vision tasks. Traditional line detectors based on the image gradient are extremely fast and accurate, but lack robustness in noisy images and challenging conditions. We propose to combine traditional and learned approaches to get the best of both worlds: an accurate and robust line detector.
  arXiv  Detail & Related papers  (2022-12-15T12:36:49Z)
• Integral Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection [78.2325219839805]
  imTED improves the state-of-the-art of few-shot object detection by up to 7.6% AP. Experiments on MS COCO dataset demonstrate that imTED consistently outperforms its counterparts by 2.8%.
  arXiv  Detail & Related papers  (2022-05-19T15:11:20Z)
• Towards Data-Efficient Detection Transformers [77.43470797296906]
  We show most detection transformers suffer from significant performance drops on small-size datasets. We empirically analyze the factors that affect data efficiency, through a step-by-step transition from a data-efficient RCNN variant to the representative DETR. We introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.
  arXiv  Detail & Related papers  (2022-03-17T17:56:34Z)
• XAI for Transformers: Better Explanations through Conservative Propagation [60.67748036747221]
  We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. Our proposal can be seen as a proper extension of the well-established LRP method to Transformers.
  arXiv  Detail & Related papers  (2022-02-15T10:47:11Z)
• DA-DETR: Domain Adaptive Detection Transformer with Information Fusion [53.25930448542148]
  DA-DETR is a domain adaptive object detection transformer that introduces information fusion for effective transfer from a labeled source domain to an unlabeled target domain. We introduce a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains. CTBlender employs the Transformer features to modulate the CNN features across multiple scales where the high-level semantic information and the low-level spatial information are fused for accurate object identification and localization.
  arXiv  Detail & Related papers  (2021-03-31T13:55:56Z)

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.