USIM Gate: UpSampling Module for Segmenting Precise Boundaries concerning Entropy

Kyungsu Lee, Haeyun Lee, Jae Youn Hwang
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:535-562, 2023.

Abstract

Deep learning (DL) techniques for precise semantic segmentation have remained a challenge because of the vague boundaries of target objects caused by the low resolution of images. Despite the improved segmentation performance using up/downsampling operations in early DL models, conventional operators cannot fully preserve spatial information and thus generate vague boundaries of target objects. Therefore, for the precise segmentation of target objects in many domains, this paper presents two novel operators: (1) upsampling interpolation method (USIM), an operator that upsamples input feature maps and combines feature maps into one while preserving the spatial information of both inputs, and (2) USIM gate (UG), an advanced USIM operator with boundary-attention mechanisms. We designed our experiments using aerial images where the boundaries critically influence the results. Furthermore, we verified the feasibility that our approach effectively segments target objects using the cityscapes dataset. The experimental results demonstrate that using the USIM and UG with state-of-the-art DL models can improve the segmentation performance with clear boundaries of target objects (Intersection over Union: +6.9$%$; BJ: +10.1$%$). Furthermore, mathematical proofs verify that the USIM and UG contribute to the handling of spatial information.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-lee23a, title = {USIM Gate: UpSampling Module for Segmenting Precise Boundaries concerning Entropy}, author = {Lee, Kyungsu and Lee, Haeyun and Hwang, Jae Youn}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {535--562}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/lee23a/lee23a.pdf}, url = {https://proceedings.mlr.press/v206/lee23a.html}, abstract = {Deep learning (DL) techniques for precise semantic segmentation have remained a challenge because of the vague boundaries of target objects caused by the low resolution of images. Despite the improved segmentation performance using up/downsampling operations in early DL models, conventional operators cannot fully preserve spatial information and thus generate vague boundaries of target objects. Therefore, for the precise segmentation of target objects in many domains, this paper presents two novel operators: (1) upsampling interpolation method (USIM), an operator that upsamples input feature maps and combines feature maps into one while preserving the spatial information of both inputs, and (2) USIM gate (UG), an advanced USIM operator with boundary-attention mechanisms. We designed our experiments using aerial images where the boundaries critically influence the results. Furthermore, we verified the feasibility that our approach effectively segments target objects using the cityscapes dataset. The experimental results demonstrate that using the USIM and UG with state-of-the-art DL models can improve the segmentation performance with clear boundaries of target objects (Intersection over Union: +6.9$%$; BJ: +10.1$%$). Furthermore, mathematical proofs verify that the USIM and UG contribute to the handling of spatial information.} }
Endnote
%0 Conference Paper %T USIM Gate: UpSampling Module for Segmenting Precise Boundaries concerning Entropy %A Kyungsu Lee %A Haeyun Lee %A Jae Youn Hwang %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-lee23a %I PMLR %P 535--562 %U https://proceedings.mlr.press/v206/lee23a.html %V 206 %X Deep learning (DL) techniques for precise semantic segmentation have remained a challenge because of the vague boundaries of target objects caused by the low resolution of images. Despite the improved segmentation performance using up/downsampling operations in early DL models, conventional operators cannot fully preserve spatial information and thus generate vague boundaries of target objects. Therefore, for the precise segmentation of target objects in many domains, this paper presents two novel operators: (1) upsampling interpolation method (USIM), an operator that upsamples input feature maps and combines feature maps into one while preserving the spatial information of both inputs, and (2) USIM gate (UG), an advanced USIM operator with boundary-attention mechanisms. We designed our experiments using aerial images where the boundaries critically influence the results. Furthermore, we verified the feasibility that our approach effectively segments target objects using the cityscapes dataset. The experimental results demonstrate that using the USIM and UG with state-of-the-art DL models can improve the segmentation performance with clear boundaries of target objects (Intersection over Union: +6.9$%$; BJ: +10.1$%$). Furthermore, mathematical proofs verify that the USIM and UG contribute to the handling of spatial information.
APA
Lee, K., Lee, H. & Hwang, J.Y.. (2023). USIM Gate: UpSampling Module for Segmenting Precise Boundaries concerning Entropy. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:535-562 Available from https://proceedings.mlr.press/v206/lee23a.html.

Related Material