Pyramidal Multiple Instance Detection Network With Mask Guided Self-Correction for Weakly Supervised Object Detection

Weakly supervised object detection has attracted more and more attention as it only needs image-level annotations for training object detectors. A popular solution to this task is to train a multiple instance detection network (MIDN) which integrates multiple instance learning into a deep convolutional neural network. One major issue of the MIDN is that it is prone to be stuck at local discriminative regions. To address this local optimum issue, we propose a pyramidal MIDN (P-MIDN) comprised of a sequence of multiple MIDNs. In particular, one MIDN performs proposal removal for its subsequent MIDN to reduce the exposure of local discriminative proposal regions to the latter during training. In this manner, it allows our MIDNs to focus on proposals which cover objects more completely. Furthermore, we integrate the P-MIDN into an online instance classifier refinement (OICR) framework. Combined with the P-MIDN, a mask guided self-correction (MCSC) method is proposed to generate high-quality pseudo ground-truths for training the OICR. Experimental results on PASCAL VOC 2007, PASCAL VOC 2010, PASCAL VOC 2012, ILSVRC 2013 DET and MS-COCO benchmarks demonstrate that our approach achieves state-of-the-art performance.

Automated summary

The proposed pyramidal multiple instance detection network (P-MIDN) addresses the issue of local optima often encountered in multiple instance detection networks. By incorporating multiple MIDNs in a sequence and using proposal removal during training to reduce exposure to local discriminative regions, the P-MIDN enables better coverage of target objects. The combination of P-MIDN with an online instance classifier refinement framework and a mask guided self-correction method results in state-of-the-art performance on various benchmark datasets.