dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test

• URL: http://arxiv.org/abs/2309.03763v1
• Date: Thu, 7 Sep 2023 15:05:35 GMT
• Title: dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test
• Authors: Johannes Flotzinger, Philipp J. R\"osch, Norbert Oswald, Thomas Braml
• Abstract summary: "dacl1k" is a multi-label RCD dataset for multi-label classification based on building inspections including 1,474 images. We trained the models on different combinations of open-source data (meta datasets) which were subsequently evaluated both extrinsically and intrinsically. The performance analysis on dacl1k shows practical usability of the meta data, where the best model shows an Exact Match Ratio of 32%.
• Score: 0.6827423171182154
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existing datasets in the RCD domain are derived from a small number of bridges acquired in specific camera poses, lighting conditions and with fixed hardware. These limitations question the usability of models trained on such open-source data in real-world scenarios. We address this problem by testing such models on our "dacl1k" dataset, a highly diverse RCD dataset for multi-label classification based on building inspections including 1,474 images. Thereby, we trained the models on different combinations of open-source data (meta datasets) which were subsequently evaluated both extrinsically and intrinsically. During extrinsic evaluation, we report metrics on dacl1k and the meta datasets. The performance analysis on dacl1k shows practical usability of the meta data, where the best model shows an Exact Match Ratio of 32%. Additionally, we conduct an intrinsic evaluation by clustering the bottleneck features of the best model derived from the extrinsic evaluation in order to find out, if the model has learned distinguishing datasets or the classes (RCDs) which is the aspired goal. The dacl1k dataset and our trained models will be made publicly available, enabling researchers and practitioners to put their models to the real-world test.

Related papers

• A CLIP-Powered Framework for Robust and Generalizable Data Selection [51.46695086779598]
  Real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance. Data selection has shown promise in identifying the most representative samples from the entire dataset. We propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection.
  arXiv  Detail & Related papers  (2024-10-15T03:00:58Z)
• On Evaluation of Vision Datasets and Models using Human Competency Frameworks [20.802372291783488]
  Item Response Theory (IRT) is a framework that infers interpretable latent parameters for an ensemble of models and each dataset item. We assess model calibration, select informative data subsets, and demonstrate the usefulness of its latent parameters for analyzing and comparing models and datasets in computer vision.
  arXiv  Detail & Related papers  (2024-09-06T06:20:11Z)
• SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection [79.23689506129733]
  We establish a new benchmark dataset and an open-source method for large-scale SAR object detection. Our dataset, SARDet-100K, is a result of intense surveying, collecting, and standardizing 10 existing SAR detection datasets. To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
  arXiv  Detail & Related papers  (2024-03-11T09:20:40Z)
• dacl10k: Benchmark for Semantic Bridge Damage Segmentation [0.0]
  "dacl10k" is an exceptionally diverse RCD dataset for semantic segmentation comprising 9,920 images deriving from real-world bridge inspections. "dacl10k" distinguishes 12 damage classes as well as 6 bridge components that play a key role in the building assessment and recommending actions.
  arXiv  Detail & Related papers  (2023-09-01T13:46:24Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [50.62245481416744]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world. We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique. By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Revisiting Table Detection Datasets for Visually Rich Documents [17.846536373106268]
  This study revisits some open datasets with high-quality annotations, identifies and cleans the noise, and aligns the annotation definitions of these datasets to merge a larger dataset, termed Open-Tables. To enrich the data sources, we propose a new ICT-TD dataset using the PDF files of Information and Communication Technologies (ICT) commodities, a different domain containing unique samples that hardly appear in open datasets. Our experimental results show that the domain differences among existing open datasets are minor despite having different data sources.
  arXiv  Detail & Related papers  (2023-05-04T01:08:15Z)
• Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study [55.964387734180114]
  Cross-modal retrieval (CMR) approaches usually focus on object-centric datasets. This paper focuses on the results and their generalizability across different dataset types. We select two state-of-the-art CMR models with different architectures. We determine the relative performance of the selected models on these datasets.
  arXiv  Detail & Related papers  (2023-01-12T18:00:00Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Label-Free Model Evaluation with Semi-Structured Dataset Representations [78.54590197704088]
  Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets. In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression. We propose a new semi-structured dataset representation that is manageable for regression learning while containing rich information for AutoEval.
  arXiv  Detail & Related papers  (2021-12-01T18:15:58Z)
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models [41.45240621979654]
  We introduce BEIR, a heterogeneous benchmark for information retrieval. We study the effectiveness of nine state-of-the-art retrieval models in a zero-shot evaluation setup. Dense-retrieval models are computationally more efficient but often underperform other approaches.
  arXiv  Detail & Related papers  (2021-04-17T23:29:55Z)
• On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets [0.0]
  Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias. This paper presents an overview of the currently public available COVID-19 chest X-ray datasets.
  arXiv  Detail & Related papers  (2020-08-26T14:16:01Z)

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.