This repository provides a PyTorch implementation and model weights for HCSC (Hierarchical Contrastive Selective Coding)

Related tags

Deep LearningHCSC
Overview

HCSC: Hierarchical Contrastive Selective Coding

This repository provides a PyTorch implementation and model weights for HCSC (Hierarchical Contrastive Selective Coding), whose details are in this paper.

HCSC is an effective and efficient method to pre-train image encoders in a self-supervised fashion. In general, this method seeks to learn image representations with hierarchical semantic structures. It utilizes hierarchical K-means to derive hierarchical prototypes, and these prototypes represent the hierarchical semantics underlying the data. On such basis, we perform Instance-wise and Prototypical Contrastive Selective Coding to inject the information within hierarchical prototypes into image representations. HCSC has achieved SOTA performance on the self-supervised pre-training of CNNs (e.g., ResNet-50), and we will further study its potential on pre-training Vision Transformers.

Roadmap

  • [2022/02/01] The initial release! We release all source code for pre-training and downstream evaluation. We release three pre-trained ResNet-50 models: 200 epochs (single-crop), 200 epochs (multi-crop) and 400 epochs (single-crop, batch size: 256).

TODO

  • Finish the pre-training of 400 epochs ResNet-50 models (multi-crop) and release.
  • Finish the pre-training of 800 epochs ResNet-50 models (single- & multi-crop) and release.
  • Support Vision Transformer backbones.
  • Pre-train Vision Transformers with HCSC and release model weights under various configurations.

Model Zoo

We will continually release our pre-trained HCSC model weights and corresponding training configs. The current finished ones are as follows:

Backbone Method Crop Epoch Batch size Lincls top-1 Acc. KNN top-1 Acc. url config
ResNet-50 HCSC Single 200 256 69.2 60.7 model config
ResNet-50 HCSC Multi 200 256 73.3 66.6 model config
ResNet-50 HCSC Single 400 256 70.6 63.4 model config

Installation

Use following command to install dependencies (python3.7 with pip installed):

pip3 install -r requirement.txt

If having trouble installing PyTorch, follow the original guidance (https://pytorch.org/). Notably, the code is tested with cudatoolkit version 10.2.

Pre-training on ImageNet

Download ImageNet dataset under [ImageNet Folder]. Go to the path "[ImageNet Folder]/val" and use this script to build sub-folders.

To train single-crop HCSC on 8 Tesla-V100-32GB GPUs for 200 epochs, run:

python3 -m torch.distributed.launch --master_port [your port] --nproc_per_node=8 \
pretrain.py [your ImageNet Folder]

To train multi-crop HCSC on 8 Tesla-V100-32GB GPUs for 200 epochs, run:

python3 -m torch.distributed.launch --master_port [your port] --nproc_per_node=8 \
pretrain.py --multicrop [your ImageNet Folder]

Downstream Evaluation

Evaluation: Linear Classification on ImageNet

With a pre-trained model, to train a supervised linear classifier with all available GPUs, run:

python3 eval_lincls_imagenet.py --data [your ImageNet Folder] \
--dist-url tcp://localhost:10001 --world-size 1 --rank 0 \
--pretrained [your pre-trained model (example:out.pth)]

Evaluation: KNN Evaluation on ImageNet

To reproduce the KNN evaluation results with a pre-trained model using a single GPU, run:

python3 -m torch.distributed.launch --master_port [your port] --nproc_per_node=1 eval_knn.py \
--checkpoint_key state_dict \
--pretrained [your pre-trained model] \
--data [your ImageNet Folder]

Evaluation: Semi-supervised Learning on ImageNet

To fine-tune a pre-trained model with 1% or 10% ImageNet labels with 8 Tesla-V100-32GB GPUs, run:

1% of labels:

python3 -m torch.distributed.launch --nproc_per_node 8 --master_port [your port] eval_semisup.py \
--labels_perc 1 \
--pretrained [your pretrained weights] \
[your ImageNet Folder]

10% of labels:

python3 -m torch.distributed.launch --nproc_per_node 8 --master_port [your port] eval_semisup.py \
--labels_perc 10 \
--pretrained [your pretrained weights] \
[your ImageNet Folder]

Evaluation: Transfer Learning - Classification on VOC / Places205

VOC

1. Download the VOC dataset.
2. Finetune and evaluate on PASCAL VOC (with a single GPU):
cd voc_cls/ 
python3 main.py --data [your voc data folder] \
--pretrained [your pretrained weights]

Places205

1. Download the Places205 dataset (resized 256x256 version)
2. Linear Classification on Places205 (with all available GPUs):
python3 eval_lincls_places.py --data [your places205 data folder] \
--data-url tcp://localhost:10001 \
--pretrained [your pretrained weights]

Evaluation: Transfer Learning - Object Detection on VOC / COCO

1. Download VOC and COCO Dataset (under ./detection/datasets).

2. Install detectron2.

3. Convert a pre-trained model to the format of detectron2:

cd detection
python3 convert-pretrain-to-detectron2.py [your pretrained weight] out.pkl

4. Train on PASCAL VOC/COCO:

Finetune and evaluate on VOC (with 8 Tesla-V100-32GB GPUs):
cd detection
python3 train_net.py --config-file ./configs/pascal_voc_R_50_C4_24k_hcsc.yaml \
--num-gpus 8 MODEL.WEIGHTS out.pkl
Finetune and evaluate on COCO (with 8 Tesla-V100-32GB GPUs):
cd detection
python3 train_net.py --config-file ./configs/coco_R_50_C4_2x_hcsc.yaml \
--num-gpus 8 MODEL.WEIGHTS out.pkl

Evaluation: Clustering Evaluation on ImageNet

To reproduce the clustering evaluation results with a pre-trained model using all available GPUs, run:

python3 eval_clustering.py --dist-url tcp://localhost:10001 \
--multiprocessing-distributed --world-size 1 --rank 0 \
--num-cluster [target num cluster] \
--pretrained [your pretrained model weights] \
[your ImageNet Folder]

In the experiments of our paper, we set --num-cluster as 25000 and 1000.

License

This repository is released under the MIT license as in the LICENSE file.

Citation

If you find this repository useful, please kindly consider citing the following paper:

@article{guo2022hcsc,
  title={HCSC: Hierarchical Contrastive Selective Coding},
  author={Guo, Yuanfan and Xu, Minghao and Li, Jiawen and Ni, Bingbing and Zhu, Xuanyu and Sun, Zhenbang and Xu, Yi},
  journal={arXiv preprint arXiv:2202.00455},
  year={2022}
}
Owner
YUANFAN GUO
From SJTU. Working on self-supervised pre-training.
YUANFAN GUO
An efficient PyTorch implementation of the evaluation metrics in recommender systems.

recsys_metrics An efficient PyTorch implementation of the evaluation metrics in recommender systems. Overview • Installation • How to use • Benchmark

Xingdong Zuo 12 Dec 02, 2022
This is a collection of our NAS and Vision Transformer work.

AutoML - Neural Architecture Search This is a collection of our AutoML-NAS work iRPE (NEW): Rethinking and Improving Relative Position Encoding for Vi

Microsoft 828 Dec 28, 2022
Hard cater examples from Hopper ICLR paper

CATER-h Honglu Zhou*, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf (*Contact: honglu.zhou

NECLA ML Group 6 May 11, 2021
Hand-distance-measurement-game - Hand Distance Measurement Game

Hand Distance Measurement Game This is program is made to calculate the distance

Priyansh 2 Jan 12, 2022
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

3d-ken-burns This is a reference implementation of 3D Ken Burns Effect from a Single Image [1] using PyTorch. Given a single input image, it animates

Simon Niklaus 1.4k Dec 28, 2022
2021 Artificial Intelligence Diabetes Datathon

A.I.D.D. 2021 2021 Artificial Intelligence Diabetes Datathon A.I.D.D. 2021은 ‘2021 인공지능 학습용 데이터 구축사업’을 통해 만들어진 학습용 데이터를 활용하여 당뇨병을 효과적으로 예측할 수 있는가에 대한 A

2 Dec 27, 2021
Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility ICCV2021

Vis2Mesh This is the offical repository of the paper: Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Lear

71 Dec 25, 2022
ML models implementation practice

Let's implement various ML algorithms with numpy/tf Vanilla Neural Network https://towardsdatascience.com/lets-code-a-neural-network-in-plain-numpy-ae

Jinsoo Heo 4 Jul 04, 2021
HiFT: Hierarchical Feature Transformer for Aerial Tracking (ICCV2021)

HiFT: Hierarchical Feature Transformer for Aerial Tracking Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, and Yiming Li Our paper is Accepted by ICCV 2

Intelligent Vision for Robotics in Complex Environment 55 Nov 23, 2022
PECOS - Prediction for Enormous and Correlated Spaces

PECOS - Predictions for Enormous and Correlated Output Spaces PECOS is a versatile and modular machine learning (ML) framework for fast learning and i

Amazon 387 Jan 04, 2023
Totally Versatile Miscellanea for Pytorch

Totally Versatile Miscellania for PyTorch Thomas Viehmann [email protected] Thi

Thomas Viehmann 428 Dec 28, 2022
SPTAG: A library for fast approximate nearest neighbor search

SPTAG: A library for fast approximate nearest neighbor search SPTAG SPTAG (Space Partition Tree And Graph) is a library for large scale vector approxi

Microsoft 4.3k Jan 01, 2023
[NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators"

G-PATE This is the official code base for our NeurIPS 2021 paper: "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of T

AI Secure 14 Oct 12, 2022
[ICCV '21] In this repository you find the code to our paper Keypoint Communities

Keypoint Communities In this repository you will find the code to our ICCV '21 paper: Keypoint Communities Duncan Zauss, Sven Kreiss, Alexandre Alahi,

Duncan Zauss 262 Dec 13, 2022
Source code for paper "Deep Diffusion Models for Robust Channel Estimation", TBA.

diffusion-channels Source code for paper "Deep Diffusion Models for Robust Channel Estimation". Generic flow: Use 'matlab/main.mat' to generate traini

The University of Texas Computational Sensing and Imaging Lab 15 Dec 22, 2022
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models.

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models

AdvBox 1.3k Dec 25, 2022
iBOT: Image BERT Pre-Training with Online Tokenizer

Image BERT Pre-Training with iBOT Official PyTorch implementation and pretrained models for paper iBOT: Image BERT Pre-Training with Online Tokenizer.

Bytedance Inc. 435 Jan 06, 2023
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"

BEGAN in Tensorflow Tensorflow implementation of BEGAN: Boundary Equilibrium Generative Adversarial Networks. Requirements Python 2.7 or 3.x Pillow tq

Taehoon Kim 922 Dec 21, 2022
Distributed Asynchronous Hyperparameter Optimization in Python

Hyperopt: Distributed Hyperparameter Optimization Hyperopt is a Python library for serial and parallel optimization over awkward search spaces, which

6.5k Jan 01, 2023
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction [arXiv] [Project Page] @inproceedings{ huang2021fapn, title={{FaPN}: Feature-alig

EMI-Group 175 Dec 30, 2022