Ensemble-based Semi-supervised Learning to Improve Noisy Soiling Annotations in Autonomous Driving
Manual annotation of soiling on surround view cameras is a very challenging and expensive task. The unclear boundary for various soiling categories like water drops or mud particles usually results in a large variance in the annotation quality. As a result, the models trained on such poorly annotated data are far from being optimal. In this paper, we focus on handling such noisy annotations via pseudo-label driven ensemble model which allow us to quickly spot problematic annotations and in most cases also sufficiently fixing them. We train a soiling segmentation model on both noisy and refined labels and demonstrate significant improvements using the refined annotations. It also illustrates that it is possible to effectively refine lower cost coarse annotations.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingPseudo LabelSimilar Papers 제목 키워드 기반
Spectral nature of soiling and its impact on multi-junction based concentrator systems
Soiling, which consists of dust, dirt and particles accumulated on the surface of conventional or concentrator photovoltaic modules, absorbs, scatters, and reflects part of the incoming sunlight. Therefore, it reduces th…
DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels
The impact of soiling on solar panels is an important and well-studied problem in renewable energy sector. In this paper, we present the first convolutional neural network (CNN) based approach for solar panel soiling and…
GPUSemi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification
In recent years, deep learning has vastly improved the identification and diagnosis of various diseases in plants. In this report, we investigate the problem of pathology classification using images of a single leaf. We …
General ClassificationPrivate Semi-supervised Knowledge Transfer for Deep Learning from Noisy Labels
Deep learning models trained on large-scale data have achieved encouraging performance in many real-world tasks. Meanwhile, publishing those models trained on sensitive datasets, such as medical records, could pose serio…
Transfer LearningData-driven soiling detection in PV modules
Soiling is the accumulation of dirt in solar panels which leads to a decreasing trend in solar energy yield and may be the cause of vast revenue losses. The effect of soiling can be reduced by washing the panels, which i…
Time SeriesTime Series Analysis