Deep Learning Face Representation by Joint Identification-Verification
This work addresses face recognition for applications like security and identification, representing a strong specific gain rather than a foundational breakthrough.
The paper tackled face recognition by developing DeepID2 features using joint identification and verification supervision in deep convolutional networks, achieving 99.15% face verification accuracy on LFW and reducing the error rate by 67% compared to prior deep learning results.
The key challenge of face recognition is to develop effective feature representations for reducing intra-personal variations while enlarging inter-personal differences. In this paper, we show that it can be well solved with deep learning and using both face identification and verification signals as supervision. The Deep IDentification-verification features (DeepID2) are learned with carefully designed deep convolutional networks. The face identification task increases the inter-personal variations by drawing DeepID2 extracted from different identities apart, while the face verification task reduces the intra-personal variations by pulling DeepID2 extracted from the same identity together, both of which are essential to face recognition. The learned DeepID2 features can be well generalized to new identities unseen in the training data. On the challenging LFW dataset, 99.15% face verification accuracy is achieved. Compared with the best deep learning result on LFW, the error rate has been significantly reduced by 67%.