Linkage Based Face Clustering via Graph Convolution Network

Abstract

In this paper, we present an accurate and scalable approach to the face clustering task. We aim at grouping a set of faces by their potential identities. We formulate this task as a link prediction problem: a link exists between two faces if they are of the same identity. The key idea is that we find the local context in the feature space around an instance (face) contains rich information about the linkage relationship between this instance and its neighbors. By constructing sub-graphs around each instance as input data, which depict the local context, we utilize the graph convolution network (GCN) to perform reasoning and infer the likelihood of linkage between pairs in the sub-graphs. Experiments show that our method is more robust to the complex distribution of faces than conventional methods, yielding favorably comparable results to state-of-the-art methods on standard face clustering benchmarks, and is scalable to large datasets. Furthermore, we show that the proposed method does not need the number of clusters as prior, is aware of noises and outliers, and can be extended to a multi-view version for more accurate clustering accuracy.

Learning to Adapt Invariance in Memory for Person Re-identification

“…inspired by spatial based methods and proposes a graphbased positive prediction (GPP) approach to predict reliable neighbors across graphs formed by different candidates. The proposed GPP is also related to LBFC [46] and SGGNN [37], which are designed for face clustering and re-ID re-ranking, respectively. The main difference is that GPP is designed to explore reliable neighbors that contribute to generalize re-ID networks.…”

Temporal Reasoning Graph for Activity Recognition

“…Due to their convincing performance and high interpretability of modeling object relationships, GCNs has been widely applied in many computer vision task which needs to explore the relation of different vision instance. In terms of applications, existing works has led to considerable performance improvement by using GCNs in traditional computer vision tasks [2], for example, skeleton-based action recognition [25], [48], link prediction [45], [49], semi-supervised classification [15], hashing [22], [23], [56], person-reid [24], and multi-label image recognition [3], and etc.…”

RRGCCAN: Re-Ranking via Graph Convolution Channel Attention Network for Person Re-Identification

“…In addition, for link prediction task, it is towards to predicting if two member nodes in a complex network should be connected or not. The approach like in [17] was developed in order to evaluate the likelihood of links. Inspired by the above works, a predictive model for the similarity inference on pedestrian graph data is being integrated into the proposed framework.…”