# Improving Weakly-Supervised Object Localization By Micro-Annotation

Source: [Improving Weakly-Supervised Object Localization By Micro-Annotation](<https://www.sota2.com/research/paper/68fa627a1e209131ce9f96f3>)

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

Data updated: 2025-10-25T20:20:33.540Z

Authors: Alexander Kolesnikov, Christoph H. Lampert

Published: 2016-05-18T12:06:35.000Z

## Abstract

Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network's mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation.

## 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.

- [Semantic Segmentation on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-test.md>): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 53.2.

- [Semantic Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-val.md>): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 51.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1605.05538>)

[PDF](<https://arxiv.org/pdf/1605.05538.pdf>)