US 12,283,082 B1
Method and system for quantifying semantic variance between neural network representations
Hao Chen, Nanjing (CN); and Haoran Zhou, Nanjing (CN)
Assigned to SOUTHEAST UNIVERSITY, Nanjing (CN)
Appl. No. 18/844,395
Filed by SOUTHEAST UNIVERSITY, Nanjing (CN)
PCT Filed Apr. 30, 2024, PCT No. PCT/CN2024/090949
§ 371(c)(1), (2) Date Sep. 6, 2024,
PCT Pub. No. WO2025/020619, PCT Pub. Date Jan. 30, 2025.
Claims priority of application No. 202310922777.2 (CN), filed on Jul. 26, 2023.
Int. Cl. G06V 10/75 (2022.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/755 (2022.01) [G06V 10/7715 (2022.01); G06V 10/82 (2022.01)] 8 Claims
OG exemplary drawing
 
1. A method for quantifying semantic variance between neural network representations, comprising the following steps:
S1: extracting representations: predicting, on a reference dataset, with two neural networks required for feature extraction, and in the prediction process, retaining an intermediate layer output of the neural networks when predicting each sample;
S2: learning weights: learning a weight of each filter in an intermediate layer corresponding to each semantic concept on the reference dataset using a Net2Vec method;
S3: calculating set IoU: linearly superimposing, using the weights learned in step S2, activation values of the filters in the intermediate layer output retained in step S1 to obtain a total activation value corresponding to each semantic concept, then binarizing the total activation value to obtain a mask of each sample corresponding to each semantic concept, and calculating the set IoU of each representation corresponding to each semantic concept; and
S4: integrating variance: calculating a variance between the set IoU of the representations of the two neural networks for all semantic concepts, and integrating the variance to obtain semantic variance between two neural network representations.