RecycleTrashNet:Strengthening Training Efficiency for Trash Classification via Composite Pooling
In this paper,we propose RecycleTrashNet to classify house trash based on deep neural networks.In our model,we use 3×3 filter in convolution layer instead of 7×7 filter,which is a smaller filter tends to learn more features.Since single max pooling or average pooling in pooling layer cant achieve good performance,we present composite pooling to preserve as many image features as possible.Experiments on trash dataset from Stanford University demonstrate good performance of RecycleTrashNet over other neural network models in speed and accuracy.It can improve training efficiency,which achieves classification results with 88%test accuracy at only 80 epochs.
Deep residual network Composite pooling Trash classification Residual block
He-qun YANG Ting LU Wen-jing GUO Shan CHANG Jia-fei SONG
School of Computer Science and Technology,Donghua University,Shanghai 200000,China
国际会议
武汉
英文
77-82
2020-01-12（万方平台首次上网日期，不代表论文的发表时间）