Age-Invariant Face Recognition by Multi-Feature Fusionand Decomposition with Self-attention

Abstract

Different from general face recognition, age-invariant face recognition (AIFR) aims at matching faces with a big age gap. Previous discriminative methods usually focus on decomposing facial feature into age-related and age-invariant components, which suffer from the loss of facial identity information. In this article, we propose a novel Multi-feature Fusion and Decomposition (MFD) framework for age-invariant face recognition, which learns more discriminative and robust features and reduces the intra-class variants. Specifically, we first sample multiple face images of different ages with the same identity as a face time sequence. Then, the multi-head attention is employed to capture contextual information from facial feature series, extracted by the backbone network. Next, we combine feature decomposition with fusion based on the face time sequence to ensure that the final age-independent features effectively represent the identity information of the face and have stronger robustness against the aging process. Besides, we also mitigate imbalanced age distribution in the training data by a re-weighted age loss. We experimented with the proposed MFD over the popular CACD and CACD-VS datasets, where we show that our approach improves the AIFR performance than previous state-of-the-art methods. We simultaneously show the performance of MFD on LFW dataset.

Fine-grained precise-bone age assessment by integrating prior knowledge and recursive feature pyramid network

“…We found that the levels of the 13 ROIs in a hand X-ray image are correlated to each other, the Pearson correlation coefficients of the 13 ROIs are calculated and shown in Table 1. To further benefit from the correlation coefficients, we implement a simple and effective self-attention mechanism [41,42] within the Densenet. As in Fig.…”

Weakly supervised spatial–temporal attention network driven by tracking and consistency loss for action detection

“…In ResNet(2+1)D [16], new convolution kernels were explored and the C3D model was optimized in terms of parameters and running speed. Video-based 3D multi-scale detection [17,18] [19][20][21] are particularly important for streaming data processing in the machine-learning field, for example, task-adaptive attention method [22] used in image captioning and self-attention and multi-feature fusion method [23] used in face recognition. Inspired by human vision, the Institute for Human-Machine Communication from Munich University Germany proposed a fast and real-time video action detection method (You Only Watch Once, YOWO) [24], which achieves the highest efficiency at present.…”

CWcollab: Presenting multimedia with web-based context-aware collaboration

“…With the boosted development of artificial intelligence in the recent decade, we also witnessed research works [28] , [29] , [30] , [31] , [32] integrating machine learning approaches into multimedia like image retrieval and face recognition. For example, Yan et al [28] introduced a multi-view deep neural network into the hash learning domain to significantly improve the performance in image retrieval.…”