.png){kind=icon}
返回
Hard Pixel Mining for Depth Privileged Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2020.3035231.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semantic segmentation has achieved remarkable progress but remains challenging due to the complex scene, object occlusion, and so on. Some research works have attempted to use extra information such as a depth map to help RGB based semantic segmentation because the depth map could provide complementary geometric cues. However, due to the inaccessibility of depth sensors, depth information is usually unavailable for the test images. In this paper, we leverage only the depth of training images as the privileged information to mine the hard pixels in semantic segmentation, in which depth information is only available for training images but not available for test images. Specifically, we propose a novel Loss Weight Module, which outputs a loss weight map by employing two depth-related measurements of hard pixels: Depth Prediction Error and Depth-aware Segmentation Error. The loss weight map is then applied to segmentation loss, with the goal of learning a more robust model by paying more attention to the hard pixels. Besides, we also explore a curriculum learning strategy based on the loss weight map. Meanwhile, to fully mine the hard pixels on different scales, we apply our loss weight module to multi-scale side outputs. Our hard pixels mining method achieves the state-of-the-art results on three benchmark datasets, and even outperforms the methods which need depth input during testing.
Keyword:
Semantics
Image segmentation
Training
Task analysis
Fuses
Measurement uncertainty
Testing
Semantic segmentation
hard samples mining
privileged information
RGBD semantic segmentation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
Recent Development of Dual-Dictionary Learning Approach in Medical Image Analysis and ReconstructionOAAI
OAAI分享收藏Preparation and microwave dielectric properties of BPO4 ceramics with ultra-low dielectric constant
PREAI
分享收藏
查看更多内容