Deep face attributes recognition using spatial transformer network

Face alignment is very crucial to the task of face attributes recognition. The performance of face attributes recognition would notably degrade if the fiducial points of the original face images are not precisely detected due to large lighting, pose and occlusion variations. In order to alleviate this problem, we propose a spatial transform based deep CNNs to improve the performance of face attributes recognition. In this approach, we first learn appropriate transformation parameters by a carefully designed spatial transformer network called LoNet to align the original face images, and then recognize the face attributes based on the aligned face images using a deep network called ClNet. To the best of our knowledge, this is the first attempt to use spatial transformer network in face attributes recognition task. Extensive experiments on two large and challenging databases (CelebA and LFWA) clearly demonstrate the effectiveness of the proposed approach over the current state-of-the-art.