Image encoding
AssigneeFujitsu Limited
InventorsNaga Sri Krishna Chaitanya DEVAGUPTAPU, Sumukh K AITHAL
Life of this patent
Estimating the term…
Abstract
A computer-implemented method comprising performing a training process, the training process comprising: using first and second image encoder networks, generating first and second sets of embeddings based on a pair of first and second input images, respectively; generating first and second nearest neighbor graphs, NNGs, based on the first and second sets of embeddings, respectively; using at least one graph neural network, GNN, extracting first and second representations from the first and second NNGs, respectively; and adjusting at least one network weight of the first image encoder network based on a difference between the first and second representations.
Claims20
A computer-implemented method comprising performing a training process, the training process comprising:
- using first and second image encoder networks, generating first and second sets of embeddings based on a pair of first and second input images, respectively;
- generating first and second nearest neighbor graphs, NNGs, based on the first and second sets of embeddings, respectively;
- using at least one graph neural network, GNN, extracting first and second representations from the first and second NNGs, respectively;
- and
- adjusting at least one network weight of the first image encoder network based on a difference between the first and second representations.
A computer program which, when run on a computer, causes the computer to carry out a method comprising performing a training process, the training process comprising:
- using first and second image encoder networks, generating first and second sets of embeddings based on a pair of first and second input images, respectively;
- generating first and second nearest neighbor graphs, NNGs, based on the first and second sets of embeddings, respectively;
- using at least one graph neural network, GNN, extracting first and second representations from the first and second NNGs, respectively;
- and
- adjusting at least one network weight of the first image encoder network based on a difference between the first and second representations.
An information processing apparatus comprising a memory and a processor connected to the memory, wherein the processor is configured to perform a training process, the training process comprising:
- using first and second image encoder networks, generating first and second sets of embeddings based on a pair of first and second input images, respectively;
- generating first and second nearest neighbor graphs, NNGs, based on the first and second sets of embeddings, respectively;
- using at least one graph neural network, GNN, extracting first and second representations from the first and second NNGs, respectively;
- and
- adjusting at least one network weight of the first image encoder network based on a difference between the first and second representations.
Dependencies are inferred from the claim text.