Improving image classifiers for small datasets by learning rate adaptations

2019 16th International Conference on Machine Vision Applications (MVA)(2019)

引用 9|浏览0
暂无评分
摘要
Our paper introduces an efficient combination of established techniques to improve classifier performance, in terms of accuracy and training time. We achieve two-fold to ten-fold speedup in nearing state of the art accuracy, over different model architectures, by dynamically tuning the learning rate. We find it especially beneficial in the case of a small dataset, where reliability of machine reasoning is lower. We validate our approach by comparing our method versus vanilla training on CIFAR-10. We also demonstrate its practical viability by implementing on an unbalanced corpus of diagnostic images.
更多
查看译文
关键词
training time,nearing state,learning rate,datasets,machine reasoning,vanilla training,diagnostic images,rate adaptations,efficient combination,classifier performance,image classifiers,model architectures,two-fold to ten-fold speedup,unbalanced corpus
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要