# Two-phase weakly supervised object detection with pseudo ground truth mining

arXiv: https://arxiv.org/abs/2104.00231 · HTML: https://mlsanity.com/paper/2104.00231/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 1 Apr 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Weakly Supervised Cascaded Convolutional Networks](https://mlsanity.com/paper/1611.08258/) (2016)
- [Towards Precise End-to-end Weakly Supervised Object Detection Network](https://mlsanity.com/paper/1911.12148/) (2019)
- [Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning](https://mlsanity.com/paper/1503.00949/) (2015)
- [ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization](https://mlsanity.com/paper/1609.04331/) (2016)
- [Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning](https://mlsanity.com/paper/1802.09129/) (2018)
- [Zigzag Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1804.09466/) (2018)
- [Weakly Supervised Object Localization Using Things and Stuff Transfer](https://mlsanity.com/paper/1703.08000/) (2017)
- [Relaxed Multiple-Instance SVM with Application to Object Discovery](https://mlsanity.com/paper/1510.01027/) (2015)
- [Deep Patch Learning for Weakly Supervised Object Classification and Discovery](https://mlsanity.com/paper/1705.02429/) (2017)

## Abstract (arXiv)

Weakly Supervised Object Detection (WSOD), aiming to train detectors with only image-level dataset, has arisen increasing attention for researchers. In this project, we focus on two-phase WSOD architecture which integrates a powerful detector with a pure WSOD model. We explore the effectiveness of some representative detectors utilized as the second-phase detector in two-phase WSOD and propose a two-phase WSOD architecture. In addition, we present a strategy to establish the pseudo ground truth (PGT) used to train the second-phase detector. Unlike previous works that regard top one bounding boxes as PGT, we consider more bounding boxes to establish the PGT annotations. This alleviates the insufficient learning problem caused by the low recall of PGT. We also propose some strategies to refine the PGT during the training of the second detector. Our strategies suspend the training in specific epoch, then refine the PGT by the outputs of the second-phase detector. After that, the algorithm continues the training with the same gradients and weights as those before suspending. Elaborate experiments are conduceted on the PASCAL VOC 2007 dataset to verify the effectiveness of our methods. As results demonstrate, our two-phase architecture improves the mAP from 49.17% to 53.21% compared with the single PCL model. Additionally, the best PGT generation strategy obtains a 0.7% mAP increment. Our best refinement strategy boosts the performance by 1.74% mAP. The best results adopting all of our methods achieve 55.231% mAP which is the state-of-the-art performance.