[NeurIPS-2021] Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Related tags

Deep LearningMosaicKD
Overview

MosaicKD

Code for NeurIPS-21 paper "Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data"

1. Motivation

Natural images share common local patterns. In MosaicKD, these local patterns are first dissembled from OOD data and then assembled to synthesize in-domain data, making OOD-KD feasible.

2. Method

MosaicKD establishes a four-player minimax game between a generator G, a patch discriminator D, a teacher model T and a student model S. The generator, as those in prior GANs, takes as input a random noise vector and learns to mosaic synthetic in-domain samples with locally-authentic and globally-legitimate distributions, under the supervisions back-propagated from the other three players.

3. Reproducing our results

3.1 Prepare teachers

Please download our pre-trained models from Dropbox (266 M) and extract them as "checkpoints/pretrained/*.pth". You can also train your own models as follows:

python train_scratch.py --lr 0.1 --batch-size 256 --model wrn40_2 --dataset cifar100

3.2 OOD-KD: CIFAR-100 (ID) + CIFAR10 (OOD)

  • Vanilla KD (Blind KD)

    python kd_vanilla.py --lr 0.1 --batch-size 128 --teacher wrn40_2 --student wrn16_1 --dataset cifar100 --unlabeled cifar10 --epoch 200 --gpu 0 
  • Data-Free KD (DFQAD)

    python kd_datafree.py --lr 0.1 --batch-size 256 --teacher wrn40_2 --student wrn16_1 --dataset cifar100 --unlabeled cifar10 --epoch 200 --lr 0.1 --local 1 --align 1 --adv 1 --balance 10 --gpu 0
  • MosaicKD (This work)

    python kd_mosaic.py --lr 0.1 --batch-size 256 --teacher wrn40_2 --student wrn16_1 --dataset cifar100 --unlabeled cifar10 --epoch 200 --lr 0.1 --local 1 --align 1 --adv 1 --balance 10 --gpu 0

3.3 OOD-KD: CIFAR-100 (ID) + ImageNet/Places365 OOD Subset (OOD)

  • Prepare 32x32 datasets
    Please prepare the 32x32 ImageNet following the instructions from https://patrykchrabaszcz.github.io/Imagenet32/ and extract them as "data/ImageNet_32x32/train" and "data/ImageNet_32x32/val". You can prepare Places365 in the same way.

  • MosaicKD on OOD subset
    As ImageNet & Places365 contain a large number of in-domain samples, we construct OOD subset for training. Please run the scripts with ''--ood_subset'' to enable subset selection.

    python kd_mosaic.py --lr 0.1 --batch-size 256 --teacher wrn40_2 --student wrn16_1 --dataset cifar100 --unlabeled cifar10 --epoch 200 --lr 0.1 --local 1 --align 1 --adv 1 --balance 10 --ood_subset --gpu 0

4. Visualization of synthetic data

5. Citation

If you found this work useful for your research, please cite our paper:

@article{fang2021mosaicking,
  title={Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data},
  author={Gongfan Fang and Yifan Bao and Jie Song and Xinchao Wang and Donglin Xie and Chengchao Shen and Mingli Song},
  journal={arXiv preprint arXiv:2110.15094},
  year={2021}
}
Owner
ZJU-VIPA
Laboratory of Visual Intelligence and Pattern Analysis
ZJU-VIPA
Some methods for comparing network representations in deep learning and neuroscience.

Generalized Shape Metrics on Neural Representations In neuroscience and in deep learning, quantifying the (dis)similarity of neural representations ac

Alex Williams 45 Dec 27, 2022
Power Core Simulator!

Power Core Simulator Power Core Simulator is a simulator based off the Roblox game "Pinewood Builders Computer Core". In this simulator, you can choos

BananaJeans 1 Nov 13, 2021
Survival analysis (SA) is a well-known statistical technique for the study of temporal events.

DAGSurv Survival analysis (SA) is a well-known statistical technique for the study of temporal events. In SA, time-to-an-event data is modeled using a

Rahul Kukreja 1 Sep 05, 2022
Official implementation of the NeurIPS'21 paper 'Conditional Generation Using Polynomial Expansions'.

Conditional Generation Using Polynomial Expansions Official implementation of the conditional image generation experiments as described on the NeurIPS

Grigoris 4 Aug 07, 2022
A curated list of neural rendering resources.

Awesome-of-Neural-Rendering A curated list of neural rendering and related resources. Please feel free to pull requests or open an issue to add papers

Zhiwei ZHANG 43 Dec 09, 2022
Cycle Consistent Adversarial Domain Adaptation (CyCADA)

Cycle Consistent Adversarial Domain Adaptation (CyCADA) A pytorch implementation of CyCADA. If you use this code in your research please consider citi

Hyunwoo Ko 2 Jan 10, 2022
Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

L2F - Learning to Forget for Meta-Learning Sungyong Baik, Seokil Hong, Kyoung Mu Lee Source code for CVPR 2020 paper "Learning to Forget for Meta-Lear

Sungyong Baik 29 May 22, 2022
"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.

SOLQ: Segmenting Objects by Learning Queries This repository is an official implementation of the paper SOLQ: Segmenting Objects by Learning Queries.

MEGVII Research 179 Jan 02, 2023
Official implementation for paper: A Latent Transformer for Disentangled Face Editing in Images and Videos.

A Latent Transformer for Disentangled Face Editing in Images and Videos Official implementation for paper: A Latent Transformer for Disentangled Face

InterDigital 108 Dec 09, 2022
A Tensorflow implementation of CapsNet based on Geoffrey Hinton's paper Dynamic Routing Between Capsules

CapsNet-Tensorflow A Tensorflow implementation of CapsNet based on Geoffrey Hinton's paper Dynamic Routing Between Capsules Notes: The current version

Huadong Liao 3.8k Dec 29, 2022
A library for answering questions using data you cannot see

A library for computing on data you do not own and cannot see PySyft is a Python library for secure and private Deep Learning. PySyft decouples privat

OpenMined 8.5k Jan 02, 2023
This repository contains a toolkit for collecting, labeling and tracking object keypoints

This repository contains a toolkit for collecting, labeling and tracking object keypoints. Object keypoints are semantic points in an object's coordinate frame.

ETHZ ASL 13 Dec 12, 2022
This computer program provides a reference implementation of Lagrangian Monte Carlo in metric induced by the Monge patch

This computer program provides a reference implementation of Lagrangian Monte Carlo in metric induced by the Monge patch. The code was prepared to the final version of the accepted manuscript in AIST

Marcelo Hartmann 2 May 06, 2022
Team Enigma at ArgMining 2021 Shared Task: Leveraging Pretrained Language Models for Key Point Matching

Team Enigma at ArgMining 2021 Shared Task: Leveraging Pretrained Language Models for Key Point Matching This is our attempt of the shared task on Quan

Manav Nitin Kapadnis 12 Jul 08, 2022
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020 Oral) Figure: Face image editing controlled via style images and segmenta

Peihao Zhu 579 Dec 30, 2022
This repository contains the files for running the Patchify GUI.

Repository Name Train-Test-Validation-Dataset-Generation App Name Patchify Description This app is designed for crop images and creating smal

Salar Ghaffarian 9 Feb 15, 2022
PyTorch implementation of our ICCV paper DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection.

Introduction This repo contains the official PyTorch implementation of our ICCV paper DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection. Up

133 Dec 29, 2022
An open source Jetson Nano baseboard and tools to design your own.

My Jetson Nano Baseboard This basic baseboard gives the user the foundation and the flexibility to design their own baseboard for the Jetson Nano. It

NVIDIA AI IOT 57 Dec 29, 2022
Free like Freedom

This is all very much a work in progress! More to come! ( We're working on it though! Stay tuned!) Installation Open an Anaconda Prompt (in Windows, o

2.3k Jan 04, 2023
Deep Learning ❤️ OneFlow

Deep Learning with OneFlow made easy 🚀 ! Carefree? carefree-learn aims to provide CAREFREE usages for both users and developers. User Side Computer V

21 Oct 27, 2022