论文标题
基于上下文的深度学习体系结构，具有最佳集成层用于图像解析
Context-based Deep Learning Architecture with Optimal Integration Layer for Image Parsing
论文作者
论文摘要
深度学习模型最近在图像解析任务上有效。但是，深度学习模型并不能完全能够同时利用视觉和上下文信息。提出的基于上下文的深度体系结构能够将上下文与视觉信息明确整合。这里的新颖想法是要有一个视觉层，以从基于二进制的班级学习者，学习上下文的上下文层学习视觉特征，然后通过基于遗传算法的最佳融合来学习上下文的上下文层，然后学习两者，以产生最终的决定。在基准数据集上评估时，实验结果是有希望的。进一步的分析表明，优化的网络权重可以提高性能并做出稳定的预测。
Deep learning models have been efficient lately on image parsing tasks. However, deep learning models are not fully capable of exploiting visual and contextual information simultaneously. The proposed three-layer context-based deep architecture is capable of integrating context explicitly with visual information. The novel idea here is to have a visual layer to learn visual characteristics from binary class-based learners, a contextual layer to learn context, and then an integration layer to learn from both via genetic algorithm-based optimal fusion to produce a final decision. The experimental outcomes when evaluated on benchmark datasets are promising. Further analysis shows that optimized network weights can improve performance and make stable predictions.
