This is the pytorch code for the paper Unsupervised Learning of Compositional Energy Concepts. Demo Please download a pretrained model at this link and then execute the following code to test a pretrained CelebA-HQ 128×128 COMET model python demo.py im_path=im0.png Please utilize the following command to run global factor decomposition on CelebA-HQ (or other datasets) python train.py –exp=celebahq –batch_size=12 –gpus=1 –cuda –train –dataset=celebahq –step_lr=500.0 You may further run the code on high-resolution 128×128 images below python train.py –exp=celebahq_128    

CFLOW-AD CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing FlowsWACV 2022 preprint:https://arxiv.org/abs/2107.12571 Abstract Unsupervised anomaly detection with localization has many practical applications when labeling is infeasible and, moreover, when anomaly examples are completely missing in the train data. While recently proposed models for such data setup achieve high accuracy metrics, their complexity is a limiting factor for real-time processing. In this paper, we propose a real-time model and analytically derive its relationship to prior methods. Our CFLOW-AD model […]

RUC This repo is the PyTorch codes for “Improving Unsupervised Image Clustering With Robust Learning (RUC)” Improving Unsupervised Image Clustering With Robust Learning Sungwon Park, Sungwon Han, Sundong Kim, Danu Kim, Sungkyu Park, Seunghoon Hong, Meeyoung Cha. Highlight RUC is an add-on module to enhance the performance of any off-the-shelf unsupervised learning algorithms. RUC is inspired by robust learning. It first divides clustered data points into clean and noisy set, then refine the clustering results. With RUC, state-of-the-art unsupervised clustering […]