In this paper we introduce plan2vec, an unsupervised representation learning approach that is inspired by reinforcement learning.
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting.
Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI.
In this work, we investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations.
In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency.
Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision.
We evaluate our self-supervised trained TCE model by adding a classification layer and finetuning the learned representation on the downstream task of video action recognition on the UCF101 dataset.
#3 best model for Self-Supervised Action Recognition on UCF101
Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks.
Disjoint Manifold Labeling: Neural Bayes allows us to formulate an objective which can optimally label samples from disjoint manifolds present in the support of a continuous distribution.