Face Attribute
Classification & Attribute-Based Classifiers
We have been working on attribute-based classifiers that allow describing or searching an object by its attributes. We are working in particular on face and plant attributes and zero-shot learning.
Recent Publications:
§ Sara
Atito Ali Ahmed, Berrin A. Yanikoglu:
Within-Network Ensemble
for Face Attributes Classification. ICIAP (1) 2019: 466-476
Building an ensemble of deep learners is very time consuming and the benefits often not very significant since the ensembles are often highly correlated. In this work we propose a within-network ensemble, that is an ensemble of 5 networks trained within one deep network, by adding extra output layers to 4 earlier layers.
§ Sara
Atito Aly, Berrin A. Yanikoglu:
Multi-Label Networks for
Face Attributes Classification. ICME
Workshops 2018: 1-6
In this work, we explore the benefits of ‘pointing to an attribute’ (indicating rough location) while training
the attribute classifier. For instance, in training for smiley/not smiley, we
tell the network that it involves the mouth region by blurring the image except
for the mouth region. Results show that pointing speeds up learning, but
requires the training to continue with the original image for max performance.