Integral Object Mining via Online Attention Accumulation

Peng-Tao Jiang, Qibin Hou, Yang Cao, Ming-Ming Cheng, Yunchao Wei, Hong-Kai Xiong; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2070-2079

Abstract


Object attention maps generated by image classifiers are usually used as priors for weakly-supervised segmentation approaches. However, normal image classifiers produce attention only at the most discriminative object parts, which limits the performance of weakly-supervised segmentation task. Therefore, how to effectively identify entire object regions in a weakly-supervised manner has always been a challenging and meaningful problem. We observe that the attention maps produced by a classification network continuously focus on different object parts during training. In order to accumulate the discovered different object parts, we propose an online attention accumulation (OAA) strategy which maintains a cumulative attention map for each target category in each training image so that the integral object regions can be gradually promoted as the training goes. These cumulative attention maps, in turn, serve as the pixel-level supervision, which can further assist the network in discovering more integral object regions. Our method (OAA) can be plugged into any classification network and progressively accumulate the discriminative regions into integral objects as the training process goes. Despite its simplicity, when applying the resulting attention maps to the weakly-supervised semantic segmentation task, our approach improves the existing state-of-the-art methods on the PASCAL VOC 2012 segmentation benchmark, achieving a mIoU score of 66.4% on the test set. Code is available at https://mmcheng.net/oaa/.

Related Material


[pdf]
[bibtex]
@InProceedings{Jiang_2019_ICCV,
author = {Jiang, Peng-Tao and Hou, Qibin and Cao, Yang and Cheng, Ming-Ming and Wei, Yunchao and Xiong, Hong-Kai},
title = {Integral Object Mining via Online Attention Accumulation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}