Repurposing GANs A minimal implementation of Repurposing GANs for One-shot Semantic Part Segmentation. w/ interactive jupyter notebook labelling tool One-Shot Segmentation Results from CNN-S trained for 100 steps with a single annotated image label_sample One-Shot SegmentationResults from CNN-S trained for 100 steps with a single annotated image    

score_sde_pytorch PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral). This repo contains a PyTorch implementation for the paper Score-Based Generative Modeling through Stochastic Differential Equations by Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole What does this code do? Aside from the NCSN++ and DDPM++ models in our paper, this codebase also re-implements many previous score-based models in one place, including NCSN from Generative Modeling by Estimating Gradients of […]

MI-AOD This is the code for Multiple Instance Active Learning for Object Detection, CVPR 2021. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images […]