SCIENCE@home

SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels

Han Yang,Tianyu Wang,Xiaowei Hu,Chi-Wing Fu

Published 2023 in IEEE International Conference on Computer Vision

ABSTRACT

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label Tuning framework, which explicitly considers noise in shadow labels and trains the deep model in a self-training manner. Specifically, we incorporate strong data augmentations with shadow counterfeiting to help the network better recognize non-shadow regions and alleviate overfitting. We also devise a simple yet effective label tuning strategy with global-local fusion and shadow-aware filtering to encourage the network to make significant refinements on the noisy labels. We evaluate the performance of SILT by relabeling the test set of the SBU [55] dataset and conducting various experiments. Our results show that even a simple U-Net [42] trained with SILT can outperform all state-of-the-art methods by a large margin. When trained on SBU / UCF [78] / ISTD [56], our network can successfully reduce the Balanced Error Rate by 25.2% / 36.9% / 21.3% over the best state-of-the-art method.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-81 of 81 references · Page 1 of 1

CITED BY

Showing 1-18 of 18 citing papers · Page 1 of 1