# Zigzag Learning for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/1804.09466 · HTML: https://mlsanity.com/paper/1804.09466/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2018.

## Built on by (most cited first, 24 of 24)

- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Class Attention Transfer Based Knowledge Distillation](https://mlsanity.com/paper/2304.12777/) (2023)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Towards Unsupervised Object Detection From LiDAR Point Clouds](https://mlsanity.com/paper/2311.02007/) (2023)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters](https://mlsanity.com/paper/2108.01499/) (2021)
- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [CAM-loss: Towards Learning Spatially Discriminative Feature Representations](https://mlsanity.com/paper/2109.01359/) (2021)
- [CTRL-O: Language-Controllable Object-Centric Visual Representation Learning](https://mlsanity.com/paper/2503.21747/) (2025)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Complete Instances Mining for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2402.07633/) (2024)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [Self-Supervised Object Detection via Generative Image Synthesis](https://mlsanity.com/paper/2110.09848/) (2021)
- [Online Active Proposal Set Generation for Weakly Supervised Object Detection](https://mlsanity.com/paper/2101.07929/) (2021)
- [Two-phase weakly supervised object detection with pseudo ground truth mining](https://mlsanity.com/paper/2104.00231/) (2021)
- [Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2110.09060/) (2021)
- [Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection](https://mlsanity.com/paper/2204.06899/) (2022)
- [Online progressive instance-balanced sampling for weakly supervised object detection](https://mlsanity.com/paper/2206.10324/) (2022)
- [HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection](https://mlsanity.com/paper/2406.19394/) (2024)
- [Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection](https://mlsanity.com/paper/2509.08289/) (2025)

## Abstract (arXiv)

This paper addresses weakly supervised object detection with only image-level supervision at training stage. Previous approaches train detection models with entire images all at once, making the models prone to being trapped in sub-optimums due to the introduced false positive examples. Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds. Towards this goal, we first develop a criterion named mean Energy Accumulation Scores (mEAS) to automatically measure and rank localization difficulty of an image containing the target object, and accordingly learn the detector progressively by feeding examples with increasing difficulty. In this way, the model can be well prepared by training on easy examples for learning from more difficult ones and thus gain a stronger detection ability more efficiently. Furthermore, we introduce a novel masking regularization strategy over the high level convolutional feature maps to avoid overfitting initial samples. These two modules formulate a zigzag learning process, where progressive learning endeavors to discover reliable object instances, and masking regularization increases the difficulty of finding object instances properly. We achieve 47.6% mAP on PASCAL VOC 2007, surpassing the state-of-the-arts by a large margin.