Clustering and Classification Networks
This work addresses a domain-specific problem in computer vision by enhancing classification accuracy, though it appears incremental as it builds on existing network architectures.
The paper tackles the problem of improving classification performance on datasets of various sizes by introducing a network architecture that sequentially learns, clusters similar classes using L1 distance on Softmax outputs, and reclassifies with clustering masks, achieving state-of-the-art results with an error rate of 11.56% on CIFAR-100.
In this paper, we will describe a network architecture that demonstrates high performance on various sizes of datasets. To do this, we will perform an architecture search by dividing the fully connected layer into three levels in the existing network architecture. The first step is to learn existing CNN layer and existing fully connected layer for 1 epoch. The second step is clustering similar classes by applying L1 distance to the result of Softmax. The third step is to reclassify using clustering class masks. We accomplished the result of state-of-the-art by performing the above three steps sequentially or recursively. The technology recorded an error of 11.56% on Cifar-100.