# Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/2203.09803 · HTML: https://mlsanity.com/paper/2203.09803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Adversarial Complementary Learning for Weakly Supervised Object Localization](https://mlsanity.com/paper/1804.06962/) (2018)
- [Attention-based Dropout Layer for Weakly Supervised Object Localization](https://mlsanity.com/paper/1908.10028/) (2019)
- [Compact Bilinear Pooling](https://mlsanity.com/paper/1511.06062/) (2015)
- [Self-produced Guidance for Weakly-supervised Object Localization](https://mlsanity.com/paper/1807.08902/) (2018)
- [See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification](https://mlsanity.com/paper/1901.09891/) (2019)
- [Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition](https://mlsanity.com/paper/1807.09915/) (2018)
- [Rethinking the Route Towards Weakly Supervised Object Localization](https://mlsanity.com/paper/2002.11359/) (2020)
- [Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator](https://mlsanity.com/paper/1911.10688/) (2019)
- [Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming](https://mlsanity.com/paper/1707.06397/) (2017)
- [Improved Techniques For Weakly-Supervised Object Localization](https://mlsanity.com/paper/1802.07888/) (2018)

## Abstract (arXiv)

Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption that the localization network should have similar location predictions on different versions of the same image, we propose a two-stage approach to learn more consistent localization. In the first stage, we propose a mask-based pseudo label generator algorithm, and use the pseudo-supervised learning method to initialize an object localization network. In the second stage, we propose a simple and effective method for evaluating the confidence of pseudo-labels based on classification discrimination, and by learning consistency from high-quality pseudo-labels, we further refine the localization network to get better localization performance. Experimental results show that our proposed approach achieves excellent performance in three benchmark datasets including CUB-200-2011, ImageNet-1k and Tiny-ImageNet, which demonstrates its effectiveness.