Yonsei University

Hyundai Mobis Co., Ltd.

Samsung Sds Co., Ltd.

Hye Ran Byun

Jewook Lee

Kwang Yong Lim

Sung Woo Kim

Sungho Park

Seung Jun Lee

Tae Woo Lee

Sun Hee Hwang

Wonyoung Lee

Bo Ram Kim

Cheolhyun Mun

Sanghuk Lee

Pilhyeon Lee

Mi Rae Do

Ki Beom Hong

Seog Kyu Jeon

Yoon Seong Kang

Minsong Ki

Dae Yong Park

Min Song Ki

Huen Oh

A weakly supervised object localization apparatus includes: a feature map generator configured to generate a feature map X by performing a first convolution operation on an input image; an erased feature map generator configured to generate an attention map A through the feature map X and generate an erased feature map −X by performing a masking operation on the input image through the attention map A; a final map generator configured to generate a final feature map F and a final erased feature map −F, respectively, by performing a second convolution operation on the feature map X and the erased feature map −X; and a contrastive guidance determiner configured to determine contrastive guidance for a foreground object in the input image based on the final feature map F and the final erased feature map −F.

Weakly supervised object localization apparatus and method

Disclosed are a CAM-based weakly supervised object localization device and method. The device includes: a feature map extractor configured to extract a feature map of a last convolutional layer in a convolutional neural network (CNN) in a process of applying an image to the CNN; a weight vector binarization unit configured to first binarize a weight vector of a linear layer in a process of sequentially applying the feature map to a pooling layer that generates a feature vector and the linear layer that generates a class label; a feature map binarization unit configured to second binarize the feature map based on the first binarized weight vector; and a class activation map generation unit configured to generate a class activation map for object localization based on the second binarized feature map.

CAM-based weakly supervised learning object localization device and method

A multi-level transferable region-based domain adaptive object detection apparatus includes: an image-level feature part that extracts an image-level feature by providing unlabeled target data to a plurality of convolutional layers; an RPN-level feature part that determines region candidates by providing the image-level feature to a region proposal network (RPN) and performing RPN-level domain adaptation and transferable region filtering; and an instance-level feature part that extracts a region of interest (RoI) pooling feature by conducting dynamic instance sampling on the region candidates.

Multi-level transferable region-based domain adaptive object detection apparatus and method

Provided is a method for generating a foreground in a foreground generating apparatus, the method including: extracting a plurality of foregrounds by applying a plurality of background models to an image, the plurality of background models having different ranges of a pixel variance value; generating an intersection foreground based on an intersection region among the extracted plurality of foregrounds; generating a union foreground based on a union region among the extracted plurality of foregrounds; and generating a final foreground based on the intersection foreground and the union foreground.

Method for generating foreground using multiple background models and apparatus thereof

A method and apparatus for detecting and recognizing a traffic sign using a modified census transform (MCT) feature are disclosed. The traffic sign recognizing method according to an exemplary embodiment of the present invention includes detecting a traffic sign candidate region from an input image using a modified census transform (MCT) feature; verifying whether the candidate region corresponds to a traffic sign using the MCT feature histogram for the candidate region; and lassifying a region of interest into the corresponding traffic sign step by step using the MCT feature histogram for the verified candidate region.

Apparatus and method for recognizing traffic sign board

Growing community of inventors

Seoul, South Korea

Hye Ran Byun