# Salvage of Supervision in Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/2106.04073 · HTML: https://mlsanity.com/paper/2106.04073/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (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)
- [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](https://mlsanity.com/paper/2004.04725/) (2020)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection](https://mlsanity.com/paper/1909.04972/) (2019)
- [Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection](https://mlsanity.com/paper/2010.12023/) (2020)
- [Towards Precise End-to-end Weakly Supervised Object Detection Network](https://mlsanity.com/paper/1911.12148/) (2019)
- [Learning from Noisy Anchors for One-stage Object Detection](https://mlsanity.com/paper/1912.05086/) (2019)
- [Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection](https://mlsanity.com/paper/1803.09867/) (2018)
- [SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection](https://mlsanity.com/paper/2006.12884/) (2020)
- [Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer](https://mlsanity.com/paper/2007.07986/) (2020)
- [Dissimilarity Coefficient based Weakly Supervised Object Detection](https://mlsanity.com/paper/1811.10016/) (2018)

## Built on by (most cited first, 8 of 8)

- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Complete Instances Mining for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2402.07633/) (2024)
- [Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth](https://mlsanity.com/paper/2303.10937/) (2023)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2303.14999/) (2023)
- [Negative Prototypes Guided Contrastive Learning for WSOD](https://mlsanity.com/paper/2406.18576/) (2024)
- [Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion](https://mlsanity.com/paper/2409.09616/) (2024)

## Abstract (arXiv)

Weakly supervised object detection~(WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper proposes new approaches to utilize these weak and noisy signals effectively, and shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also has the ability to freely use modern FSOD techniques. SoS-WSOD achieves 64.4 mAP50 on VOC2007, 61.9 mAP50 on VOC2012 and 16.6 mAP50:95 on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.