Abstract: There is provided a learning method and a learning device for performing transfer learning on an object detector that has been trained to detect first object classes such that the object detector is able to detect second object classes. Further, a testing method and a testing device are provided to allow at least part of the first object classes and the second object classes to be detected by using the object detector having been trained through the transfer learning. Accordingly, a detection performance can be improved for the second object classes that cannot be detected through training data set corresponding to the first object classes.

Abstract: A method for generating an object detector based on deep learning capable of detecting an extended object class is provided. The method is related to generating the object detector based on the deep learning capable of detecting the extended object class to thereby allow both an object class having been trained and additional object class to be detected. According to the method, it is possible to generate the training data set necessary for training an object detector capable of detecting the extended object class at a low cost in a short time and further it is possible to generate the object detector capable of detecting the extended object class at a low cost in a short time.

Abstract: A method for tracking an object in a low frame rate video is provided. Matching processes are performed between consecutive frames by using conversion feature maps acquired by converting each of features on feature maps of the consecutive frames into feature descriptors including each corresponding feature information and each corresponding location information, thereby allowing object tracking regardless of whether time interval per frame is long or short. The object tracking is performed by matching feature descriptors on a plurality of pyramid feature maps on an entire area of a next frame and feature descriptors on a plurality of cropped feature maps generated by cropping object areas extracted on a current frame, thereby allowing not only quick matching between the cropped areas and the entire area but also the increased accuracy due to no limitation of the feature searching area.

Abstract: A method of generating training data for a deep learning network is provided.

Abstract: A method for auto-labeling images by using a class-agnostic refinement module is provided. The method includes steps of: (a) an auto-labeling device inputting the images into a coverage controlling module, to thereby allow the coverage controlling module to label objects on the images and thus to output first labeling data including first object region data and first class data; (b) the auto-labeling device inputting the images and the first object region data into the class-agnostic refinement module, to thereby allow the class-agnostic refinement module to label the objects on the images and thus to generate second object region data, and allowing the class-agnostic refinement module to align the first object region data and the second object region data to thereby output refined object region data; and (c) the auto-labeling device generating second labeling data including the first class data and the refined object region data.

Abstract: A method for training an auto labeling device performing automatic verification using uncertainty of labels is provided. The method includes steps of: a learning device (a) (i) inputting unlabeled training images into (i-1) an object detection network to generate bounding boxes for training and (i-2) a convolution network to generate feature maps for training, and (ii) allowing an ROI pooling layer to generate pooled feature maps for training and inputting the pooled feature maps for training into a deconvolution network to generate segmentation masks for training; and (b) (i) inputting the pooled feature maps for training into at least one of (i-1) a first classifier to generate first per-pixel class scores for training and first mask uncertainty scores for training and (i-2) a second classifier to generate second per-pixel class scores for training and second mask uncertainty scores for training and (ii) training the first classifier or the second classifier.

Abstract: A method for training an auto-labeling device is provided. The method includes: (a) inputting a training image to a pre-trained feature extraction module to generate a feature, (b) inputting the feature to a pre-trained first classification module to output a first class score and a first uncertainty score, inputting the feature to a pre-trained second classification module, to output a second class score and a second uncertainty score, generating a scaled second uncertainty score by applying a scale parameter to the second uncertainty score, and then inputting the feature to a fitness estimation module to output a fitness value; and (c) (i) updating the scale parameter by using an uncertainty loss generated based on the first uncertainty score and the scaled second uncertainty score, and (ii) training the fitness estimation module by using a cross-entropy loss generated based on the uncertainty loss and the fitness value.

Abstract: A method for training an auto labeling device capable of performing automatic verification by using uncertainty scores of labels is provided. The method includes steps of: a learning device (a) inputting unlabeled training images into a trained object detection network and a trained convolution network to generate bounding boxes for training and feature maps for training; and (b) (i) instructing an ROI pooling layer to generate pooled feature maps for training, (ii) at least one of (ii-1) inputting the pooled feature maps for training into a first classifier to generate first class scores for training and first box uncertainty scores for training, and (ii-2) inputting the pooled feature maps for training into a second classifier to generate second class scores for training and second box uncertainty scores for training, and (iii) training one of the first classifier using first class losses and the second classifier using second class losses.

Abstract: A method for training an auto labeling device performing verification using uncertainty scores of auto-labeled labels is provided. The method includes steps of: a learning device (a) (i) inputting first unlabeled images into a feature pyramid network (FPN) to generate first pyramid feature maps, (ii) allowing an object detection network to generate first bounding boxes, and (iii) training the object detection network and the FPN; (b) (i) allowing the FPN to generate second pyramid feature maps and allowing the object detection network to generate second bounding boxes, (ii) instructing an ROI pooling layer to generate pooled feature maps and inputting the pooled feature maps into at least one of a first classifier to generate first class scores and first box uncertainty scores, and a second classifier to generate second class scores and second box uncertainty scores and (iii) training one of the first classifier and the second classifier.

Abstract: A method of training an auto labeling device is provided. The method includes steps of: a learning device (a) inputting first images into an FPN to generate first pyramid feature maps, instructing an object detection network (ODN) to generate first bounding boxes, an ROI pooling layer to generate first pooled feature maps, and a deconvolution network to generate first segmentation masks, and training the ODN, the FPN, and the deconvolution network and (b) inputting second images into the FPN to generate second pyramid feature maps, and instructing the ODN to generate second bounding boxes, the ROI pooling layer to generate second pooled feature maps, and the deconvolution network to generate second segmentation masks, and inputting the second pooled feature maps into at least one of first and second classifiers to generate per-pixel class scores and mask uncertainty scores, and training one of the first and the second classifiers.

Abstract: A method for generating training data for a deep learning network is provided.