Object Instance Mining for Weakly Supervised Object Detection


  • Chenhao Lin SenseTime Research
  • Siwen Wang Dalian University of Technology
  • Dongqi Xu SenseTime Research
  • Yu Lu SenseTime Research
  • Wayne Zhang SenseTime Research




Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years. Existing approaches using multiple instance learning easily fall into local optima, because such mechanism tends to learn from the most discriminative object in an image for each category. Therefore, these methods suffer from missing object instances which degrade the performance of WSOD. To address this problem, this paper introduces an end-to-end object instance mining (OIM) framework for weakly supervised object detection. OIM attempts to detect all possible object instances existing in each image by introducing information propagation on the spatial and appearance graphs, without any additional annotations. During the iterative learning process, the less discriminative object instances from the same class can be gradually detected and utilized for training. In addition, we design an object instance reweighted loss to learn larger portion of each object instance to further improve the performance. The experimental results on two publicly available databases, VOC 2007 and 2012, demonstrate the efficacy of proposed approach.




How to Cite

Lin, C., Wang, S., Xu, D., Lu, Y., & Zhang, W. (2020). Object Instance Mining for Weakly Supervised Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11482-11489. https://doi.org/10.1609/aaai.v34i07.6813



AAAI Technical Track: Vision