Knowledge Commons of Institute of Automation,CAS
Consistent-Separable Feature Representation for Semantic Segmentation | |
He XJ(何兴建)1,2; Liu J(刘静)1,2; Fu J(付君)2; Wang JQ(王金桥)2; Lu HQ(卢汉清)1,2 | |
2021-05-08 | |
会议名称 | Proceedings of the AAAI Conference on Artificial Intelligence |
卷号 | 35 |
期号 | 2 |
页码 | 1531-1539 |
会议日期 | 2021-2-2 |
会议地点 | online |
摘要 | Cross-entropy loss combined with softmax is one of the most commonly used supervision components in most existing segmentation methods. The softmax loss is typically good at optimizing the inter-class difference, but not good at reducing the intra-class variation, which can be suboptimal for semantic segmentation task. In this paper, we propose a Consistent-Separable Feature Representation Network to model the Consistent-Separable (C-S) features, which are intra-class consistent and inter-class separable, improving the discriminative power of the deep features. Specifically, we develop a Consistent-Separable Feature Learning Module to obtain C-S features through a new loss, called Class-Aware Consistency loss. This loss function is proposed to force the deep features to be consistent among the same class and apart between different classes. Moreover, we design an Adaptive feature Aggregation Module to fuse the C-S features and original features from backbone for the better semantic prediction. We show that compared with various baselines, the proposed method brings consistent performance improvement. Our proposed approach achieves state-of-the-art performance on Cityscapes (82.6% mIoU in test set), ADE20K (46.65% mIoU in validation set), COCO Stuff (41.3% mIoU in validation set) and PASCAL Context (55.9% mIoU in test set). |
关键词 | Consistent-Separable Feature Class-Aware Consistency loss Semantic Segmentation |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48887 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
通讯作者 | Liu J(刘静) |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | He XJ,Liu J,Fu J,et al. Consistent-Separable Feature Representation for Semantic Segmentation[C],2021:1531-1539. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Consistent-Separable(591KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论