Method and apparatus with recognition model training

An apparatus comprising:

• one or more processors configured to:
• generate a first sample image and a second sample image by performing data augmentation on an input training image;
• generate a first feature map of the first sample image and a second feature map of the second sample image by performing feature extraction on the first sample image and the second sample image using an encoding model;
• determine first loss data according to a relationship between first feature vectors of the first feature map and second feature vectors of the second feature map;
• estimate relative geometric information of the first feature map and the second feature map using a relationship estimation model;
• determine second loss data according to the relative geometric information, based on label data according to a geometric arrangement of the first sample image and the second sample image in the input training image;
• and
• train the encoding model and the relationship estimation model, based on the first loss data and the second loss data.

An apparatus comprising:

• one or more processors configured to generate a feature map of an image by performing feature extraction on the image using a trained encoding model,
• wherein the encoding model is trained based on first loss data and second loss data,
• wherein the first loss data is determined based on first feature vectors of a first feature map and second feature vectors of a second feature map, and the first feature map and the second feature map are generated by performing feature extraction respectively on a first sample image and a second sample image using the encoding model, and
• wherein the second loss data is determined based on estimated relative geometric information of the first feature map and the second feature map, and the relative geometric information is estimated using a relationship estimation model.