# Convolutional STN for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/1912.01522 · HTML: https://mlsanity.com/paper/1912.01522/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 6 of 6)

- [F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling](https://mlsanity.com/paper/2109.07069/) (2021)
- [TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2208.14542/) (2022)
- [Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues](https://mlsanity.com/paper/2402.00281/) (2024)
- [CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos](https://mlsanity.com/paper/2303.09044/) (2023)
- [Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos](https://mlsanity.com/paper/2407.06018/) (2024)
- [SecurePose: Automated Face Blurring and Human Movement Kinematics Extraction from Videos Recorded in Clinical Settings](https://mlsanity.com/paper/2402.14143/) (2024)

## Abstract (arXiv)

Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance. State-of-the-art methods recycle the architecture of a standard CNN by using the activation maps of the last layer for localizing the object. While this approach is simple and works relatively well, object localization relies on different features than classification, thus, a specialized localization mechanism is required during training to improve performance. In this paper, we propose a convolutional, multi-scale spatial localization network that provides accurate localization for the object of interest. Experimental results on CUB-200-2011 and ImageNet datasets show that our proposed approach provides competitive performance for weakly supervised localization.