Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels. Under the online scenario, data is in the form of streams, i.e., the whole dataset could not be accessed at the same time and the model should be able to make cluster assignments for new data without accessing the former data.
Image Credit: Online Clustering by Penalized Weighted GMM
Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches.
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space.
We address the problem of face clustering in long, real world videos. This is a challenging task because faces in such videos exhibit wid evariability in scale, pose, illumination, expressions, and may also be partially occluded.
Our experiments on a variety of datasets, and both in stationary and non-stationary environments of several kinds demonstrate clear advantages of the proposed adaptive representation learning over the standard contextual bandit based on "raw" input contexts.