用于边界检测的有向边缘森林算法
Oriented Edge Forests for Boundary Detection
摘要:
我们提出了一个简单,有效的学习边界检测模型的基础上的随机森林分类。我们的方法结合了(1)有效的聚类的训练样本的基础上简单的分区的空间的局部边缘方向和(2)规模依赖校准的个别树输出概率之前,多尺度组合。由此产生的模型优于具有挑战性的BSDS500边界检测基准公布的结果。此外,在大型数据集上,我们的模型需要更少的内存来进行训练,并且与结构化森林模型相比,训练时间加快了10倍。
英文摘要:
We present a simple, efficient model for learning boundary detection based on a random forest classifier. Our approach combines (1) efficient clustering of training examples based on simple partitioning of the space of local edge orientations and (2) scale-dependent calibration of individual tree output probabilities prior to multiscale combination. The resulting model outperforms published results on the challenging BSDS500 boundary detection benchmark. Further, on large datasets our model requires substantially less memory for training and speeds up training time by a factor of 10 over the structured forest model.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。