.png){kind=icon}
返回
Context-aware co-supervision for accurate object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108199.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
State-of-the-art object detection approaches are often composed of two stages, namely, proposing a number of regions on an image and classifying each of them into one class. Both stages share a network backbone which builds visual features in a bottom-up manner. In this paper, we advocate the importance of equipping two-stage detectors with top-down signals, in order to which provides high-level contextual cues to complement low-level features. In practice, this is implemented by adding a side path in the detection head to predict all object classes in the image, which is co-supervised by image-level semantics and requires little extra overheads. Our approach is easily applied to two popular object detection algorithms, and achieves consistent performance gain in the MS-COCO dataset. (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Object detection
Co-supervised
Contextual cues
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
MDFN: Multi-scale deep feature learning network for object detectionMDFN: 用于目标检测的多尺度深度特征学习网络.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Multi-model ensemble with rich spatial information for object detectionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
没有更多内容
没有更多内容