Systems and methods for deep model translation generation

Abstract

Embodiments of the present invention relate to systems and methods for improving the training of machine learning systems to recognize certain objects within a given image by supplementing an existing sparse set of real-world training images with a comparatively dense set of realistic training images. Embodiments may create such a dense set of realistic training images by training a machine learning translator with a convolutional autoencoder to translate a dense set of synthetic images of an object into more realistic training images. Embodiments may also create a dense set of realistic training images by training a generative adversarial network (“GAN”) to create realistic training images from a combination of the existing sparse set of real-world training images and either Gaussian noise, translated images, or synthetic images. The created dense set of realistic training images may then be used to more effectively train a machine learning object recognizer to recognize a target object in a newly presented digital image.

The invention claimed is: 
     
         1 . A method for improving the training of a computer-based object recognizer to recognize a target object within an image selected from a set of real-world images, the method comprising:
 training a translator to produce a set of translated images of the target object, said translator comprising a first computer-based machine learning system;   training the computer-based object recognizer to recognize the target object within a newly presented digital image by providing the object recognizer a collection of training images, said collection of training images assembled from:   (1) a set of real-world images of the target object, and   (2) the plurality of translated images of the target object.   
     
     
         2 . The method of  claim 1  further comprising:
 creating a set of synthetic images of the target object; and 
 wherein translator training is performed using the synthetic images. 
 
     
     
         3 . The method of  claim 2  further comprising providing the translator with a plurality of pairings, where each pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set of synthetic images. 
     
     
         4 . The method of  claim 1  wherein the translator comprises a first computer-based machine learning system having a convolutional autoencoder. 
     
     
         5 . The method of  claim 1  further comprising:
 creating a set of synthetic images of the target object; 
 wherein the translator comprises a first computer-based machine learning system having a convolutional autoencoder; and 
 where translator training includes providing the translator with a plurality of pairings, where each pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set of synthetic images, and where the convolutional autoencoder learns from the pairings how to produce the set of translated images of the target object. 
 
     
     
         6 . The method of  claim 1  wherein the translator comprises a first computer-based machine learning system; and
 wherein translator training includes providing the translator with a set of images generated from a second computer-based machine learning system different from the first computer-based machine learning system. 
 
     
     
         7 . The method of  claim 6  wherein the translator training provides the translator with a plurality of second parings, where each second pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set images generated from the second computer-based machine learning system. 
     
     
         8 . The method of  claim 1  wherein the translator has a convolutional autoencoder and comprises a first computer-based machine learning system; and
 wherein translator training includes providing the translator with a plurality of second parings, where each second pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set images generated from the second computer-based machine learning system, and where the convolutional autoencoder additionally learns from the second pairings how to produce the set of translated images of the target object. 
 
     
     
         9 . The method of  claim 4  wherein the convolutional autoencoder includes a loss function that is invoked iteratively during the translator training. 
     
     
         10 . The method of  claim 1  where the object recognizer includes a loss function that is invoked iteratively during the object recognizer training. 
     
     
         11 . The method of  claim 4  wherein the convolutional autoencoder includes a first loss function that is invoked iteratively during the translator training;
 wherein the object recognizer includes a second loss function that is invoked iteratively during the object recognizer training; and 
 wherein the translator training is synchronized with the object recognizer training, where loss values from the second loss function are incorporated into calculations made by the first loss function. 
 
     
     
         12 . A computer-based object recognizer for recognizing a target object within an image selected from a set of real-world images, comprising:
 a trainable machine learning processor;   a translator processor programmed to produce a set of translated images of the target object for use in training the machine learning processor;   a training processor programmed to supply to the trainable machine learning processor with a collection of training images, assembled from:
 (a) the set of real-world images, and 
 (b) the translated images of the target object. 
   
     
     
         13 . The computer-based object recognizer of  claim 12  further comprising:
 a set of synthetic images of the target object stored in a computer-readable medium; 
 wherein the translator includes a convolutional autoencoder; 
 wherein the translator processor is programmed to ingest a plurality of pairings, where each pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set of synthetic images; and 
 wherein the convolutional autoencoder is configured to learn from the pairings how to produce the set of translated images of the target object. 
 
     
     
         14 . The computer-based object recognizer of  claim 13  wherein the translator processor is programmed to ingest a plurality of second parings, where each second pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set images generated from a computer-based machine learning system. 
     
     
         15 . The computer-based object recognizer of  claim 14  wherein the translator includes a convolutional autoencoder; and
 wherein translator processor is programmed to ingest a plurality of second parings, where each second pairing is obtained by identifying one of the set of real-world images that corresponds with one of the set images generated from the computer-based machine learning system, and where the convolutional autoencoder additionally learns from the second pairings how to produce the set of translated images of the target object. 
 
     
     
         16 . The computer-based object recognizer of  claim 13  wherein the convolutional autoencoder includes a loss function that is invoked iteratively during the translator training. 
     
     
         17 . The computer-based object recognizer of  claim 1  where the object recognizer includes a loss function that is invoked iteratively during the training of the trainable machine learning processor.