Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Runmin Cong, Xiaochun Cao, Qingming Huang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:28989-29021, 2024.

Abstract

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-li24bx, title = {Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection}, author = {Li, Feiran and Xu, Qianqian and Bao, Shilong and Yang, Zhiyong and Cong, Runmin and Cao, Xiaochun and Huang, Qingming}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {28989--29021}, 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/li24bx/li24bx.pdf}, url = {https://proceedings.mlr.press/v235/li24bx.html}, abstract = {This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method.} }
Endnote
%0 Conference Paper %T Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection %A Feiran Li %A Qianqian Xu %A Shilong Bao %A Zhiyong Yang %A Runmin Cong %A Xiaochun Cao %A Qingming Huang %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-li24bx %I PMLR %P 28989--29021 %U https://proceedings.mlr.press/v235/li24bx.html %V 235 %X This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method.
APA
Li, F., Xu, Q., Bao, S., Yang, Z., Cong, R., Cao, X. & Huang, Q.. (2024). Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:28989-29021 Available from https://proceedings.mlr.press/v235/li24bx.html.

Related Material