arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1508.00451stat.MLcs.CVcs.LGcs.NE
收藏

结构支持向量机中神经元因子的集成推理与学习

Integrated Inference and Learning of Neural Factors in Structural Support Vector Machines

Ghent University(根特大学);iMinds(iMinds研究院)

Rein Houthooft, Filip De Turck

摘要:

处理计算机视觉、生物信息学、语音或文本识别等领域的模式识别问题,通常最好是考虑输出变量之间特定于任务的统计关系。在结构化预测中,这种内部结构用于同时预测多个输出,从而实现更准确和连贯的预测。结构支持向量机(SSVM)是一种非概率模型,通过基于边缘的学习来优化联合输入输出函数。由于SSVM通常忽略训练阶段一元和交互因素之间的相互作用,最终参数是次优的。此外,它的因素往往局限于输入特征的线性组合,限制了它的泛化能力。为了提高预测精度,本文提出:(i)通过集成SSVM次梯度下降中的反向传播和损失增强推理的联合推理和学习;(ii)将SSVM因子扩展到形成输入特征的高度非线性函数的神经网络。图像分割基准测试结果表明,与传统的SSVM训练方法相比,在准确性方面有所改进,突出了使用神经因素进行端到端SSVM训练的可行性。

英文摘要:

Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this internal structure is used to predict multiple outputs simultaneously, leading to more accurate and coherent predictions. Structural support vector machines (SSVMs) are nonprobabilistic models that optimize a joint input-output function through margin-based learning. Because SSVMs generally disregard the interplay between unary and interaction factors during the training phase, final parameters are suboptimal. Moreover, its factors are often restricted to linear combinations of input features, limiting its generalization power. To improve prediction accuracy, this paper proposes: (i) Joint inference and learning by integration of back-propagation and loss-augmented inference in SSVM subgradient descent; (ii) Extending SSVM factors to neural networks that form highly nonlinear functions of input features. Image segmentation benchmark results demonstrate improvements over conventional SSVM training methods in terms of accuracy, highlighting the feasibility of end-to-end SSVM training with neural factors.

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。

↑