Rollouts gathered through training a PPO agent on Atari, originally used for evaluating unsupervised object detection/tracking networks SPAIR and SILOT.
Original tensorflow implementation of SILOT (Spatially Invariant, Label-free Object Tracking).
An Unsupervised Learning Framework for Moving Object Detection From Videos
Video object segmentation allows computer vision to identify objects as they move through the space in a given video. Here we presents One-Shot Video Object Segmentation (OSVOS), a CNN architecture to tackle the problem of semisupervised video object segmentation, that is, the classification of all pixels of a video sequence into background and foreground,given the manual annotation of one of its frames.
Using deep clustering and manifold learning to perform unsupervised learning of image clustering.
Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch
Library for running and managing machine learning experiments with tensorflow and pytorch.
Original implementation of Spatially Invariant Attend, Infer, Repeat (SPAIR) in TensorFlow.
