Beta-Rank：一种用于不平衡医学图像分析的鲁棒卷积滤波器剪枝方法
Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis
AI总结：
针对深度网络在资源受限设备上难以处理不平衡医学数据的问题，提出Beta-Rank滤波器剪枝方法，通过结合滤波器输入输出与权重值评估重要性，在大幅减少FLOPs和参数的同时保持或提升基线模型性能，并经手机应用验证了内存与预测时间的显著降低。
摘要：
由于深度神经网络包含大量参数和操作，在计算资源有限的设备上实现这些模型可能面临挑战。尽管针对资源高效模型开发了新型剪枝方法，但显而易见的是，这些模型无法处理“不平衡”和“数据点数量有限”的情况。我们提出了一种新型滤波器剪枝方法，该方法通过考虑滤波器的输入和输出以及滤波器的值，能够比其他方法更好地处理不平衡数据集。我们的剪枝方法基于这样一个事实：关于滤波器重要性的所有信息可能并未反映在滤波器的值中，而是反映在滤波器应用于数据后对数据所做的改变中。在本研究中，我们在相同训练条件下比较了三种方法（仅各方法的排名值不同），并与其他论文中的14种方法进行了比较。我们证明，对于不平衡医学数据集，我们的模型表现明显优于其他方法。例如，当我们在IDRID数据集上移除高达58%的FLOPs，在ISIC数据集上移除高达45%的FLOPs时，我们的模型能够产生与基线模型相当（甚至更优）的结果。为了在真实环境中评估使用我们模型减少FLOP和参数的效果，我们构建了一款智能手机应用程序，其中展示了内存使用量减少高达79%，预测时间减少72%。用于训练不同模型的所有代码和参数可在https://github.com/mohofar/Beta-Rank获取。
英文摘要：
As deep neural networks include a high number of parameters and operations, it can be a challenge to implement these models on devices with limited computational resources. Despite the development of novel pruning methods toward resource-efficient models, it has become evident that these models are not capable of handling "imbalanced" and "limited number of data points". We proposed a novel filter pruning method by considering the input and output of filters along with the values of the filters that deal with imbalanced datasets better than others. Our pruning method considers the fact that all information about the importance of a filter may not be reflected in the value of the filter. Instead, it is reflected in the changes made to the data after the filter is applied to it. In this work, three methods are compared with the same training conditions except for the ranking values of each method, and 14 methods are compared from other papers. We demonstrated that our model performed significantly better than other methods for imbalanced medical datasets. For example, when we removed up to 58% of FLOPs for the IDRID dataset and up to 45% for the ISIC dataset, our model was able to yield an equivalent (or even superior) result to the baseline model. To evaluate FLOP and parameter reduction using our model in real-world settings, we built a smartphone app, where we demonstrated a reduction of up to 79% in memory usage and 72% in prediction time. All codes and parameters for training different models are available at https://github.com/mohofar/Beta-Rank
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。
