Self-Supervised Learning

ClusterFit is a self-supervision approach for learning image representations. Given a dataset, we (a) cluster its features extracted from a pre-trained network using k-means and (b) re-train a new network from scratch on this dataset using cluster assignments as pseudo-labels.

Source: ClusterFit: Improving Generalization of Visual Representations

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Action Classification 1 50.00%
Image Classification 1 50.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories