The code was forked from the initial project and changed by Dmitry Medvedev. This project contains code of experiments for coursework
This repo contains code for training expert trajectories and distilling synthetic data from our Dataset Distillation by Matching Training Trajectories paper (CVPR 2022). Please see our project page for more results.
We propose BiDirectional learning for offline Infinite-width model-based optimization (BDI) between the high-scoring designs and the static dataset (a.k.a. low-scoring designs).
We propose BIB: BIdirectional Learning for Offline Model-based Biological Sequence Design, which focuses on designing biological sequences to maximize some sequence score.
Existing DD methods exhibit degraded performance when applied to imbalanced datasets, especially when the imbalance factor increases, whereas our method provides significantly better performance under different imbalanced scenarios.
The main features of ichbill/ltdd are: Other Applications.
Open-source alternatives to ichbill/ltdd include: dm-medvedev/dataset-distillation — The code was forked from the initial project and changed by Dmitry Medvedev. This project contains code of experiments… georgecazenavette/mtt-distillation — This repo contains code for training expert trajectories and distilling synthetic data from our Dataset Distillation… ggchen1997/bdi — We propose BiDirectional learning for offline Infinite-width model-based optimization (BDI) between the high-scoring… ggchen1997/bib-icml2023-submission — We propose BIB: BIdirectional Learning for Offline Model-based Biological Sequence Design, which focuses on designing… haowenguan/galaxy-dataset-distillation — This is the official repository for paper Discovering Galaxy Features via Dataset Distillation. Our work contains the… mcg-nju/video-dc — The official implementation of A Large-Scale Study on Video Action Dataset Condensation.