Soft Hough Forest-ERTs: Generalized Hough Transform based object detection from soft-labelled training data
作者：
Highlights：
• A modified soft label estimation method by selecting a reliable positive bag based on Maximum Mean Discrepancy.
• Extremely Randomized Trees are extended to learn from soft-labelled training blobs.
• Probabilistic Hough voting process is derived from soft label ERTs codebook.
• Weakly supervised object detection method is proposed.
• Experimental results show the advantage of utilizing soft labels, and the performance of the proposed weakly supervised object detection method.
摘要
Highlights•A modified soft label estimation method by selecting a reliable positive bag based on Maximum Mean Discrepancy.•Extremely Randomized Trees are extended to learn from soft-labelled training blobs.•Probabilistic Hough voting process is derived from soft label ERTs codebook.•Weakly supervised object detection method is proposed.•Experimental results show the advantage of utilizing soft labels, and the performance of the proposed weakly supervised object detection method.
论文关键词：Object detection,Weakly supervised learning,Generalized Hough Transform,Extremely Randomized Trees,Soft labels
论文评审过程：Received 26 May 2014, Revised 25 March 2016, Accepted 23 April 2016, Available online 24 May 2016, Version of Record 2 June 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.04.023
