# US 2021/0241097 A1 · Method and Apparatus for training an object recognition model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241097 A1 - Document ID: US20210241097A1 - Status: Published application - Kind: A1 - Application number: 17/089,583 - Filed: 2020-11-04 - Published: 2021-08-05 - Earliest claimed: 2019-11-07 - Applicants: Canon Kabushiki Kaisha - Inventors: Dongyue Zhao; Dongchao Wen; Xian Li; Weihong Deng; Jiani Hu - Web page: https://patentgrep.com/patent/US20210241097A1 ## CPC - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/048: Activation functions - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 40/16: Human faces, e.g. facial parts, sketches or expressions - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A training method and device for an object recognition model. An apparatus for optimizing a neural network model for object recognition, including a loss determination unit configured to determine loss data for features extracted from a training image set using the neural network model and a loss function with a weight function, and an updating unit configured to perform an updating operation on parameters of the neural network model based on the loss data and an updating function, wherein the updating function is derived based on the loss function with the weight function of the neural network model, and the weight function and the loss function change monotonically in a specific value interval in the same direction. ## Claims ### Claim 1 An apparatus for optimizing a neural network model for object recognition, comprising: a loss determination unit configured to determine loss data for features extracted from a training image set using the neural network model and a loss function with a weight function, and an updating unit configured to perform an updating operation for parameters of the neural network model based on the loss data and an updating function, wherein the updating function is derived based on the loss function with the weight function of the neural network model, and the weight function and the loss function change monotonically in a specific value interval in the same direction. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein the weight function and the loss function each is a function of angle, and wherein the angle is an intersection angle between an extracted feature mapped onto a hyperspherical manifold and a specific weight vector in a fully connected layer of the neural network model, and wherein the specific value interval is a specific angle value interval. ### Claim 3 (depends on 2) The apparatus according to claim 2, wherein the specific angle value interval is [0, π/2], and the weight function and the loss function change monotonically and smoothly in the specific angle value interval in the same direction. ### Claim 4 (depends on 2) The apparatus according to claim 2, wherein the loss function is a cosine function of the intersection angle. ### Claim 5 (depends on 1) The apparatus according to claim 1, wherein the loss function comprises an intra-class angle loss function, and wherein an intra-class angle is an intersection angle between an extracted feature mapped onto a hyperspherical manifold and a weight vector in a fully connected layer of the neural network model representing a truth object, and wherein the updating function is determined based on the intra-class angle loss function and an intra-class angle weight function. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein the intra-class angle loss function is an intra-class angle cosine function that takes negative, and the intra-class angle weight function is a function which is non-negative and increases smoothly and monotonically as the angle increases in a specific value interval. ### Claim 7 (depends on 1) The apparatus according to claim 1, wherein the value interval is [0, π/2], and the intra-class angle weight function has a horizontal cutoff point near 0. ### Claim 8 (depends on 1) The apparatus according to claim 1, wherein the loss function further comprises an inter-class angle loss function, and wherein an inter-class angle is an intersection angle between an extracted feature mapped onto a hyperspherical manifold and another weight vector in a fully connected layer of the neural network model, and wherein the updating function is determined based on the inter-class angle loss function and an inter-class angle weight function. ### Claim 9 (depends on 1) The apparatus according to claim 1, wherein the inter-class angle loss function is a sum of inter-class angle cosine functions, and the inter-class angle weight function is a function which is non-negative and decreases smoothly and monotonically as the angle increases in a specific value interval. ### Claim 10 (depends on 1) The apparatus according to claim 1, wherein the value interval is [0, π/2], and the inter-class angle weight function has a horizontal cut-off point near π/2. ### Claim 11 (depends on 1) The apparatus of claim 1, wherein the updating function is based on the weight function and a partial derivative of the loss function. ### Claim 12 (depends on 1) The apparatus according to claim 1, wherein the updating unit is further configured to multiply the partial derivative of the loss function and the weight function to determine an updating gradient for updating the neural network model. ### Claim 13 (depends on 12) The apparatus according to claim 12, wherein the updating unit is further configured to update the parameters of the neural network model using a back propagation method and the determined updating gradient. ### Claim 14 (depends on 1) The apparatus according to claim 1, wherein after the neural network model is updated, the loss determination unit and the updating unit operate by using the updated neural network model. ### Claim 15 (depends on 1) The apparatus according to claim 1, wherein the updating unit is configured to, when the determined loss data is greater than a threshold and the number of iteration operations performed by the loss determination unit and the updating unit does not reach a predetermined iteration number, perform updating by means of the determined updating gradient. ### Claim 16 (depends on 1) The apparatus according to claim 1, wherein the loss data determination unit is further configured to determine the loss data by using a combination of the weight function and the loss function of the neural network model. ### Claim 17 (depends on 1) The apparatus according to claim 1, wherein a combination of the weight function and the loss function of the neural network model is a product of the weight function and the loss function of the neural network model. ### Claim 18 (depends on 1) The apparatus according to claim 1, further comprising an image feature acquisition unit configured to acquire image features from a training image set using the neural network model. ### Claim 19 (depends on 1) The apparatus according to claim 1, wherein the neural network model is a deep neural network model, and the acquired image features are depth-embedded features of the images. ### Claim 20 (depends on 1) The apparatus of claim 1, wherein the parameters of the weight function can be adjusted based on loss data determined on a training set or a validation set. ### Claim 21 (depends on 20) The apparatus according to claim 20, wherein after a first parameter and a second parameter for the weight function are individually set for performing a loss data determination operation and an updating operation which are iterative, two parameters around one of the first and second parameters which causes the loss data to be better are selected as the first parameter and the second parameter for the weight function in the next iteration operation. ### Claim 22 (depends on 20) The apparatus according to claim 20, wherein the weight function is a Sigmoid function or its variant function having similar characteristics, and the parameters include a slope parameter and a horizontal intercept parameter. ### Claim 23 A method for training a neural network model for object recognition, comprising: a loss determination step of determining loss data for features extracted from a training image set using the neural network model and a loss function with a weight function, and an update step of performing an updating operation for parameters of the neural network model based on the loss data and an updating function, wherein the updating function is derived based on the loss function with the weight function of the neural network model, and the weight function and the loss function change monotonically in a specific value interval in the same direction. ### Claim 24 A device, comprising at least one processor; and at least one storage device on which instructions are stored, the instructions, when executed by the at least one processor, causing the at least one processor to perform a method for training a neural network model for object recognition, comprising: determining loss data for features extracted from a training image set using the neural network model and a loss function with a weight function, and performing an updating operation for parameters of the neural network model based on the loss data and an updating function, wherein the updating function is derived based on the loss function with the weight function of the neural network model, and the weight function and the loss function change monotonically in a specific value interval in the same direction. ### Claim 25 (depends on 23) A storage medium storing instructions that, when executed by a processor, cause execution of the method of claim 23.