The superiority of deeply learned pedestrian representations has been
reported in very recent literature of person re-identification (re-ID). In this
paper, we consider the more pragmatic issue of learning a deep feature with
only a few or no labels. We propose a progressive unsupervised learning (PUL)
method to transfer pretrained deep representations to unseen domains. Our
method is easy to implement and can be viewed as an effective baseline for
unsupervised feature learning. Specifically, PUL iterates between 1) pedestrian
clustering and 2) fine-tuning of the convolutional neural network (CNN) to
improve the original model trained on the irrelevant labeled dataset. At the
beginning when the model is weak, CNN is fine-tuned on a small amount of
reliable examples which locate near to cluster centroids in the feature space.
As the model becomes stronger in subsequent iterations, more images are being
selected as CNN training samples. Progressively, pedestrian clustering and the
CNN model are improved simultaneously until algorithm convergence. We then
point out promising directions that may lead to further improvement.