Unsupervised Deep Learning Image Verification Method

Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to state-of-the-art unsupervised face verification techniques. In this work, we propose a method to narrow this gap by leveraging an autoencoder to convert the face image vector into a novel representation. Notably, the autoencoder is trained to reconstruct neighboring face image vectors rather than the original …

art cs.ai cs.cv cs.cy data deep learning face gap image image recognition leads narrow performance recognition state training training data unsupervised verification work