# Improving Weakly-Supervised Object Localization By Micro-Annotation

arXiv: https://arxiv.org/abs/1605.05538 · HTML: https://mlsanity.com/paper/1605.05538/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2016.

## Built on by (most cited first, 11 of 11)

- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://mlsanity.com/paper/2203.03860/) (2022)
- [Optimizing Relevance Maps of Vision Transformers Improves Robustness](https://mlsanity.com/paper/2206.01161/) (2022)
- [Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation](https://mlsanity.com/paper/2508.06426/) (2025)
- [Explicit Tradeoffs between Adversarial and Natural Distributional Robustness](https://mlsanity.com/paper/2209.07592/) (2022)
- [Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning](https://mlsanity.com/paper/2405.20439/) (2024)
- [Shortcut Detection with Variational Autoencoders](https://mlsanity.com/paper/2302.04246/) (2023)
- [UnseenNet: Fast Training Detector for Any Unseen Concept](https://mlsanity.com/paper/2203.08759/) (2022)

## Abstract (arXiv)

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.