vios-s / CSDisentanglement_Metrics_Library
This repository constists of the implementations of the Distance Correlation (DC) and Information Over Bias (IOB) metrics proposed in [link]. The two metrics can be used to assess the level of disentanglement between spatial content and vector style representations. Both metrics are ready to use with PyTorch and TensorFlow implementations.
☆22Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for CSDisentanglement_Metrics_Library
- Code for CVPR2021 paper 'Where and What? Examining Interpretable Disentangled Representations'.☆44Updated 2 years ago
- ☆55Updated 4 years ago
- Pytorch implementation of of "Domain Intersection and Domain Difference" (ICCV 2019)☆39Updated 4 years ago
- ☆50Updated 4 years ago
- [ICLR2022] Code for "Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View"☆135Updated 2 years ago
- Code for NeurIPS 2019 paper Emergence of Object Segmentation in Perturbed Generative Models☆32Updated 5 years ago
- ☆35Updated 9 months ago
- ☆32Updated 3 years ago
- ☆22Updated 5 years ago
- Code for paper "Object landmark discovery through unsupervised adaptation"☆35Updated 4 years ago
- PyTorch Implementation of cGANTransfer☆45Updated 2 years ago
- Deep Feature Factorization☆56Updated 4 years ago
- Unsupervised Part Discovery from Contrastive Reconstruction (NeurIPS 2021)☆65Updated 11 months ago
- ☆12Updated last year
- [CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning☆84Updated 2 years ago
- [ICCVW 2021] Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement☆20Updated 3 years ago
- Official repository for HP-VAE-GAN☆56Updated 3 months ago
- ImageNet-CoG is a benchmark for concept generalization. It provides a full evaluation framework for pre-trained visual representations wh…☆25Updated 3 years ago
- Building blocks for uncertainty-aware cycle consistency presented at NeurIPS'21.☆25Updated 3 years ago
- ☆44Updated 3 years ago
- [ICML 2020] InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs☆41Updated 4 years ago
- ☆19Updated 5 years ago
- ☆23Updated 3 years ago
- Content and Style Disentanglement for Artistic Style Transfer [ICCV19]☆96Updated 3 years ago
- The official Tensorflow implementation for ECCV'20 paper 'Inclusive GAN: Improving Data and Minority Coverage in Generative Models'☆25Updated last year
- ☆26Updated 5 years ago
- ☆23Updated 2 years ago
- Code and instructions accompanying ICCV'23 paper Protoype-based Dataset Comparison☆17Updated 10 months ago
- Official code repository for Instance Selection for GANs.☆44Updated 3 years ago
- Official PyTorch implementation on ID-GAN: High-Fidelity Synthesis with Disentangled Representation by Lee et al., 2020.☆29Updated 4 years ago