# Convolutional STN for Weakly Supervised Object Localization

Source: [Convolutional STN for Weakly Supervised Object Localization](<https://www.sota2.com/research/paper/68fa68d41e209131cea1e6f1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:46:52.640Z

Authors: Akhil Meethal, Marco Pedersoli, Soufiane Belharbi, Eric Granger

Published: 2019-12-03T16:51:11.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Weakly-Supervised Object Localization on CUB (test)](<https://www.sota2.com/research/sota/weakly-supervised-object-localization-on-cub-test.md>): Weakly Supervised Object Localization; CUB (test); Top-1 Loc Acc: 49.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.01522>)

[PDF](<https://arxiv.org/pdf/1912.01522.pdf>)