ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection

Hongyu Liu, Runmin Cong, Hua Li, Qianqian Xu, Qingming Huang, Wei Zhang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30892-30907, 2024.

Abstract

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (${MAE}_{{BD}}$) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-liu24l, title = {{ESN}et: Evolution and Succession Network for High-Resolution Salient Object Detection}, author = {Liu, Hongyu and Cong, Runmin and Li, Hua and Xu, Qianqian and Huang, Qingming and Zhang, Wei}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30892--30907}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/liu24l/liu24l.pdf}, url = {https://proceedings.mlr.press/v235/liu24l.html}, abstract = {Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (${MAE}_{{BD}}$) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods.} }
Endnote
%0 Conference Paper %T ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection %A Hongyu Liu %A Runmin Cong %A Hua Li %A Qianqian Xu %A Qingming Huang %A Wei Zhang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-liu24l %I PMLR %P 30892--30907 %U https://proceedings.mlr.press/v235/liu24l.html %V 235 %X Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (${MAE}_{{BD}}$) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods.
APA
Liu, H., Cong, R., Li, H., Xu, Q., Huang, Q. & Zhang, W.. (2024). ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30892-30907 Available from https://proceedings.mlr.press/v235/liu24l.html.

Related Material