Phân tích tư tưởng của nhân dân qua đoạn thơ: Những người vợ nhớ chồng… Những cuộc đời đã hóa sông núi ta trong Đất nước của Nguyễn Khoa Điềm
3444
1
0
9 trang
In addition, a feature map is used to reformulate the sum-match kernel function as a dot product of two mean feature vectors in a mapped-feature space. Furthermore, we proposed an algorithm for learning a balanced tree which gains the computational efficiency in classification. We carried out experiments on benchmark datasets including Caltech-256, SUN-397, and ImageNet-1K. The evaluation results indicated that our method achieves a significant improvement in terms of accuracy and efficiency compared to other methods. In particular, our method achieved 14.52% in accuracy on ImageNet-1K, compared to 6.51% of the Bengio et al.’s method.
Nội dung trích xuất từ tài liệu:
Using sum match kernel with balanced label tree for large scale image classification
