Unverified50% confidenceSolutionExact time
The grouped fully connected layer gives each feature map its own n²×n² weight matrix with no connections between different feature maps, reducing the parameter count from m²n⁴ to m·n⁴.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified单应性矩阵是3×3的齐次变换矩阵，具有8个自由度，描述同一平面在两个不同相机视角下的投影关系，通过估计四对点对应关系即可唯一确定70% similarUnverifiedThe joint covariance matrix for n observation points in a full Gaussian process is of size n×n, with a direct computation time complexity of O(n³) and memory footprint of O(n²).67% similarUnverifiedHomography transformation uses a 3×3 transformation matrix H to represent the projective mapping relationship between two planes; estimating this matrix requires at least 4 pairs of corresponding points, and the DLT algorithm is typically used to solve it with RANSAC employed to eliminate outliers.65% similarUnverifiedOAL groups dimensions by contribution magnitude, where dimensions with similar contributions share coefficients and a small number of outlier dimensions are handled individually to control parameter count.63% similarUnverifiedSpectral clustering maps high-dimensional data to a low-dimensional spectral space by computing the eigenvectors of the graph Laplacian matrix, and then completes clustering with k-means.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1004196API
curl https://kongchang.com/api/v1/knowledge/claims/1004196MCP
get_claim(id=1004196)