# Zigzag Learning for Weakly Supervised Object Detection Source: [Zigzag Learning for Weakly Supervised Object Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:57:29.306Z Authors: Xiaopeng Zhang, Jiashi Feng, Hongkai Xiong, Qi Tian Published: 2018-04-25T10:26:57.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Weakly Supervised Object Localization on PASCAL VOC 2012 (trainval)](): Weakly Supervised Object Localization; PASCAL VOC 2012 (trainval); Aero CorLoc: 80.3. - [Weakly Supervised Object Localization on PASCAL VOC 2007 (trainval)](): Weakly Supervised Object Localization; PASCAL VOC 2007 (trainval); CorLoc (Aero): 80.3. - [Object Localization on PASCAL VOC 2012 (trainval)](): Object Localization; PASCAL VOC 2012 (trainval); CorLoc: 61.5. - [Object Localization on PASCAL VOC 2007 (trainval)](): Object Localization; PASCAL VOC 2007 (trainval); CorLoc: 61.2. - [Object Detection on PASCAL VOC 2012 (test)](): Object Detection; PASCAL VOC 2012 (test); mAP: 42.9. - [Object Detection on PASCAL VOC 2007 (test)](): Object Detection; PASCAL VOC 2007 (test); mAP: 47.6. ## Original sources and implementation [Original paper]() [PDF]()