Dataset for "Face Detection in Untrained Deep Neural Networks"

Dataset for "Face Detection in Untrained Deep Neural Networks" Seungdae Baek, Min Song, Jaeson Jang, Gwangsu Kim, and Se-Bum Paik* *Contact: sbpaik@kaist.ac.kr To run demo codes for "Face Detection in Untrained Deep Neural Networks", please download files below. 1. Stimulus.zip - IMG_cntr_210521.mat : A low-level feature-controlled stimulus set was used to find units that responded selectively to face images (Stigliani, 2015). Specifically, 260 images were prepared for each class (face, hand, horn, flower, chair, and scrambled face). - IMG_var_pos/size/rot_210521.mat : To investigate the invariance of face-selective units to face images of various sizes, positions, and rotation angles, the image set (Stigliani, 2015) was generated after modifying the size, position, and rotation angle of the faces and other objects in the low-level feature-controlled stimulus set. - IMG_var_view_210106.mat : This set was used to find units that invariantly responded to face images of different viewpoints. This dataset consists of five angle-based viewpoint classes (-90°, -45°, 0°, 45°, 90°) with ten different faces obtained from (Gourier 2004) 2. Data.zip - Data_PFI_XDream/RevCorr_ClsUnit.mat : The obtained preferred feature images, using reverse-correlation method and X-Dream, of units selective to each object class. - Data_SVM_NeuronType.mat : Simulated face detection performance using distinct types of selective units in Conv5 and using the shuffled responses of face-selective units in untrained networks (a. all selective units, b. units selective to non-face classes (nonface-selective), c. face-selective units, d. units selective to none of these classes (non-selective)). - Data_SVM_invariance.mat : Face detection performance with variation of the low-level features. - PretrainedNet : Sample networks was untrained and trained with three types of image sets (a. face-reduced ImageNet, b. original ImageNet, c. original ImageNet with added face images (Stigliani, 2015)) (number of networks = 3). - Net_Untrained : untrained AlexNets - Net_FD_ImageNet : AlexNets trained to face-reduced ImageNet - Net_ImageNet : AlexNets trained to original ImageNet - Net_ImageNetwFace : AlexNets trained to original ImageNet with added face images - Data_Trained.mat : Result summary of four types of networks above (number of networks = 10).