Open set recognition happens when negative classes, that are ill-sampled or not sampled at all during training, appear in system operation or testing. Vision and machine learning researchers have made great progress and are tackling bigger and bigger datasets, but have done so in a closed set paradigm. As we reduce the assumptions and controls and move toward real problems, we must face up to the fact that while we may sample tens of thousands of positive classes, we cannot sample all possible negatives – our world is effectively open and we need to embrace its openness.
In this project, we present a vision for a new fundamental theory and the corresponding set of tools designed from the ground up for open set recognition, with a particular emphasis on visual data and broad usability. At the heart of this proposal are three key concepts:
1) Designing for open set recognition — designing classifiers in the face of data with uncertain or ill-defined category membership
2) Meta-recognition — bringing a statistically-grounded probabilistic interpretation to support recognition.
3) Projective imputation and bias correction for missing data.
We present preliminary work, using linear models, on each of the three. The new theoretical constructions for the three areas provides a strong basis and the preliminary work, for each of the three areas, is at or significantly advancing the state of the art. The proposed work will expand on this strong basis, unify and integrate them and support non-linear kernels and optimized open set multiclass recognition.
We call this effort “OpenVision” for two reasons:
1) We present a vision for open set recognition problems that will advance core science in vision and machine learning.
2) We will develop open source recognition tools that will apply across many domains.
UCCSfaces is a database of unconstrained facial images captured at a distance of approximately 100 meters. This database provides the face images and the protocol for various challenge problems such as open set recognition, face clustering, re-identification etc.