MegaFace: A Million Faces for Recognition at Scale
This addresses the problem of scaling face recognition for researchers and practitioners by highlighting performance gaps in large-scale settings, though it is incremental as it focuses on evaluation rather than new methods.
The paper tackles face recognition at scale by evaluating state-of-the-art algorithms on a new dataset of one million faces, finding that performance drops drastically compared to smaller benchmarks like LFW, with deep learning methods performing better but still less robust.
Recent face recognition experiments on the LFW benchmark show that face recognition is performing stunningly well, surpassing human recognition rates. In this paper, we study face recognition at scale. Specifically, we have collected from Flickr a \textbf{Million} faces and evaluated state of the art face recognition algorithms on this dataset. We found that the performance of algorithms varies--while all perform great on LFW, once evaluated at scale recognition rates drop drastically for most algorithms. Interestingly, deep learning based approach by \cite{schroff2015facenet} performs much better, but still gets less robust at scale. We consider both verification and identification problems, and evaluate how pose affects recognition at scale. Moreover, we ran an extensive human study on Mechanical Turk to evaluate human recognition at scale, and report results. All the photos are creative commons photos and is released at \small{\url{http://megaface.cs.washington.edu/}} for research and further experiments.