Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark

by   Joakim Bruslund Haurum, et al.

Perhaps surprisingly sewerage infrastructure is one of the most costly infrastructures in modern society. Sewer pipes are manually inspected to determine whether the pipes are defective. However, this process is limited by the number of qualified inspectors and the time it takes to inspect a pipe. Automatization of this process is therefore of high interest. So far, the success of computer vision approaches for sewer defect classification has been limited when compared to the success in other fields mainly due to the lack of public datasets. To this end, in this work we present a large novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML. The Sewer-ML dataset consists of 1.3 million images annotated by professional sewer inspectors from three different utility companies across nine years. Together with the dataset, we also present a benchmark algorithm and a novel metric for assessing performance. The benchmark algorithm is a result of evaluating 12 state-of-the-art algorithms, six from the sewer defect classification domain and six from the multi-label classification domain, and combining the best performing algorithms. The novel metric is a class-importance weighted F2 score, F2_CIW, reflecting the economic impact of each class, used together with the normal pipe F1 score, F1_Normal. The benchmark algorithm achieves an F2_CIW score of 55.11 of 90.94 code, models, and dataset are available at the project page


page 1

page 6

page 10

page 11

page 12

page 16

page 17


A Capsule Network for Hierarchical Multi-Label Image Classification

Image classification is one of the most important areas in computer visi...

Semantic Comparison of State-of-the-Art Deep Learning Methods for Image Multi-Label Classification

Image understanding relies heavily on accurate multi-label classificatio...

ML-Net: multi-label classification of biomedical texts with deep neural networks

Background: Multi-label text classification is one type of text classifi...

Multi-label Node Classification On Graph-Structured Data

Graph Neural Networks (GNNs) have shown state-of-the-art improvements in...

Discriminative Kernel Convolution Network for Multi-Label Ophthalmic Disease Detection on Imbalanced Fundus Image Dataset

It is feasible to recognize the presence and seriousness of eye disease ...

Graph Unlearning

The right to be forgotten states that a data subject has the right to er...

Grading Loss: A Fracture Grade-based Metric Loss for Vertebral Fracture Detection

Osteoporotic vertebral fractures have a severe impact on patients' overa...

Please sign up or login with your details

Forgot password? Click here to reset