论文标题
专家的偏见混合物：在数据传输限制下实现计算机视觉推断
Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
论文作者
论文摘要
我们提出了一种新型的专家类别类，以根据测试时数据传输限制来优化计算机视觉模型。我们的方法假设，允许高度准确结果的最低可接受数据量可能会因不同的输入空间分区而有所不同。因此，我们考虑专家需要不同数据的混合物，并训练稀疏的门控函数，以分配每个专家的输入空间。通过适当的超参数选择，我们的方法能够使专家的混合物偏向于选择特定的专家而不是其他专家。通过这种方式，我们表明，可以将视觉传感和处理之间的数据传输优化作为凸优化问题解决。为了证明数据可用性和性能之间的关系，我们评估了主流计算机视觉问题的有偏见混合物，即：（i）单射击检测，（i）单个镜头检测，（II）图像超级分辨率和（iii II II II III）视频构图。对于所有情况，当专家构成经过改进的基线以满足允许数据实用程序的不同限制时，有偏见的混合物大大优于以前优化的工作，以满足可用数据的相同约束。
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.
