Objectness Consistent Representation for Weakly Supervised Object Detection
| Autor: | Dongsheng Li, Zhiyuan Wang, Ke Yang, Peng Qiao, Peng Zhang, Yong Dou |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
business.industry
Computer science Rank (computer programming) Consistency criterion Representation (systemics) Learning object Pattern recognition 02 engineering and technology Object (computer science) Object detection 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence business Image retrieval |
| Zdroj: | ACM Multimedia |
| DOI: | 10.1145/3394171.3413835 |
| Popis: | Weakly supervised object detection aims at learning object detectors with only image-level category labels. Most existing methods tend to solve this problem by using a multiple instance learning detector which is usually trapped to discriminate object parts. In order to select high-quality proposals, recent works leverage objectness scores derived from weakly-supervised segmentation maps to rank the object proposals. Base on our observation, this kind of segmentation guided method always fails due to neglect of the fact that the objectness of all proposals inside the ground-truth box should be consistent. In this paper, we propose a novel object representation named Objectness Consistent Representation (OCRepr) to meet the consistency criterion of objectness. Specifically, we project the segmentation confidence scores into two orthogonal directions, namely vertical and horizontal, to get the OCRepr. With the novel object representation, more high-quality proposals can be mined for learning a much stronger object detector. We obtain 54.6% and 51.1% mAP scores on VOC 2007 and 2012 datasets, significantly outperforming the state-of-the-art and demonstrating the superiority of OCRepr for weakly supervised object detection. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|