Analyzing Object-Scale Dependency of Dual-Branch Sigmoid CAM for Weakly Supervised Object Localization 


Vol. 15,  No. 4, pp. 306-314, Apr.  2026
https://doi.org/10.3745/TKIPS.2026.15.4.306


PDF
  Abstract

Class Activation Mapping (CAM) is widely used for interpreting deep visual models and enabling weakly supervised object localization (WSOL), but its reliance on softmax-based classifiers introduces competitive normalization that suppresses weak or co-occurring object evidence, often resulting in incomplete localization. In this work, we build upon our previously proposed dual-branch sigmoid architecture and conduct a systematic, scale-aware analysis to examine how decoupling localization from softmax normalization affects localization behavior across object sizes. Using the ImageNet-1K dataset, we stratify evaluation samples into small-object and large-object subsets based on ground-truth bounding box statistics and perform controlled WSOL evaluations across multiple backbones. The results show that sigmoid-based localization consistently improves localization completeness, with particularly pronounced gains for small objects, while maintaining or modestly improving performance on large objects. These findings provide empirical evidence that the limitations of softmax-based CAMs are strongly object-scale dependent and demonstrate that sigmoid-based localization effectively mitigates signal suppression in scale-sensitive WS OL scenarios, offering a practical framework for diagnosing and improving localization behavior

  Statistics
  Cite this article

[IEEE Style]

E. Ryu, H. Joo, J. Noh, "Analyzing Object-Scale Dependency of Dual-Branch Sigmoid CAM for Weakly Supervised Object Localization," The Transactions of the Korea Information Processing Society, vol. 15, no. 4, pp. 306-314, 2026. DOI: https://doi.org/10.3745/TKIPS.2026.15.4.306.

[ACM Style]

Eunhyun Ryu, Hyewon Joo, and Junhyug Noh. 2026. Analyzing Object-Scale Dependency of Dual-Branch Sigmoid CAM for Weakly Supervised Object Localization. The Transactions of the Korea Information Processing Society, 15, 4, (2026), 306-314. DOI: https://doi.org/10.3745/TKIPS.2026.15.4.306.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals