Learnt quasi-transitive similarity for retrieval from large collections of faces
This addresses the problem of face set retrieval in uncontrolled environments for applications like surveillance or social media, but it is incremental as it builds on existing baseline methods.
The paper tackles identity-based retrieval of face sets from large unlabelled collections by exploiting partial transitivity of similarity to improve retrieval for challenging sets, demonstrating effectiveness on the YouTube database with two baselines.
We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as a means of computing the similarity between two sets, (ii) introduce transitivity meta-features based on the similarity of salient modes of appearance variation between sets, (iii) show how quasi-transitivity can be learnt from such features without any labelling or manual intervention, and (iv) demonstrate the effectiveness of the proposed methodology through experiments on the notoriously challenging YouTube database and two successful baselines from the literature.