Implicit Negative Sub-Categorization and Sink Diversion for Object Detection.

IEEE Transactions on Image Processing(2018)

引用 17|浏览165
暂无评分
摘要
In this paper, we focus on improving the proposal classification stage in the object detection task and present implicit negative sub-categorization and sink diversion to lift the performance by strengthening loss function in this stage. First, based on the observation that the “background” class is generally very diverse and thus challenging to be handled as a single indiscriminative class in exi...
更多
查看译文
关键词
Proposals,Object detection,Feature extraction,Birds,Convolution,Histograms
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要