S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

Last update: Dec 24, 2022

Overview

S²-BNN (Self-supervised Binary Neural Networks Using Distillation Loss)

This is the official pytorch implementation of our paper:

"S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration" (CVPR 2021)

by Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng and Marios Savvides.

In this paper, we introduce a simple yet effective self-supervised approach using distillation loss for learning efficient binary neural networks. Our proposed method can outperform the simple contrastive learning baseline (MoCo V2) by an absolute gain of 5.5∼15% on ImageNet.

The student models are not restricted to the binary neural networks, you can replace with any efficient/compact models.

Citation

If you find our code is helpful for your research, please cite:

@InProceedings{Shen_2021_CVPR,
	author    = {Shen, Zhiqiang and Liu, Zechun and Qin, Jie and Huang, Lei and Cheng, Kwang-Ting and Savvides, Marios},
	title     = {S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-Bit Neural Networks via Guided Distribution Calibration},
	booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	year      = {2021}

}

Preparation

1. Requirements:

Python
PyTorch
Torchvision

2. Data:

Download ImageNet dataset following https://github.com/pytorch/examples/tree/master/imagenet#requirements.

Training & Testing

To train a model, run the following scripts. All our models are trained with 8 GPUs.

1. Standard Two-Step Training:

Our enhanced MoCo V2:

Step 1:

cd Contrastive_only/step1
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders]  --mlp --moco-t 0.2 --aug-plus --cos -j 48

Step 2:

cd Contrastive_only/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders]  --mlp --moco-t 0.2 --aug-plus --cos -j 48  --model-path ../step1/checkpoint_0199.pth.tar

Our MoCo V2 + Distillation Loss:

Download real-valued teacher network here. We use MoCo V2 800-epoch pretrained model, while you can choose other stronger self-supervised models as the teachers.

Step 1:

cd Contrastive+Distillation/step1
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0  --teacher-path ../../moco_v2_800ep_pretrain.pth.tar

Step 2:

cd Contrastive+Distillation/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0  --teacher-path ../../moco_v2_800ep_pretrain.pth.tar --model-path ../step1/checkpoint_0199.pth.tar

Our Distillation Loss Only:

Step 1:

cd Distillation_only/step1
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0 --teacher-path ../../moco_v2_800ep_pretrain.pth.tar

Step 2:

cd Distillation_only/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0 --teacher-path ../../moco_v2_800ep_pretrain.pth.tar --model-path ../step1/checkpoint_0199.pth.tar

2. Simple One-Step Training (Conventional):

Our enhanced MoCo V2:

cd Contrastive_only/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48

Our MoCo V2 + Distillation Loss:

cd Contrastive+Distillation/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0 --teacher-path ../../moco_v2_800ep_pretrain.pth.tar

Our Distillation Loss Only:

cd Distillation_only/step2
python main_moco.py --lr 0.0003 --batch-size 256 --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders] --mlp --moco-t 0.2 --aug-plus --cos -j 48 --wd 0 --teacher-path ../../moco_v2_800ep_pretrain.pth.tar

You can replace binary neural networks with any kinds of efficient/compact models on one-step training.

3. Testing:

To linearly evaluate a model, run the following script:

python main_lincls.py  --lr 0.1  -j 24  --batch-size 256  --pretrained  /home/szq/projects/s2bnn/checkpoint_0199.pth.tar --dist-url 'tcp://localhost:10001' --multiprocessing-distributed --world-size 1 --rank 0 [imagenet-folder with train and val folders]

Results & Models

We provide pre-trained models with different training strategies, we report in the table #epochs, OPs, Top-1 accuracy on ImageNet validation set:

Models	#Epoch	FLOPs (x10⁸)	OPs (x10⁸)	Top-1 (%)	Trained models
MoCo V2 baseline	200	0.12	0.87	46.9	Download
Our enhanced MoCo V2	200	0.12	0.87	52.5	Download
Our MoCo V2 + Distillation Loss	200	0.12	0.87	56.0	Download
Our Distillation Loss Only	200	0.12	0.87	61.5	Download

Training Logs

Our linear evaluation logs are availabe at here.

Acknowledgement

MoCo V2 (Improved Baselines with Momentum Contrastive Learning)

ReActNet (ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions)

MEAL V2 (MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks)

Contact

Zhiqiang Shen, CMU (zhiqiangshen0214 at gmail.com)

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

Related tags

Overview

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss)

Citation

Preparation

1. Requirements:

2. Data:

Training & Testing

1. Standard Two-Step Training:

Our enhanced MoCo V2:

Step 1:

Step 2:

Our MoCo V2 + Distillation Loss:

Step 1:

Step 2:

Our Distillation Loss Only:

Step 1:

Step 2:

2. Simple One-Step Training (Conventional):

Our enhanced MoCo V2:

Our MoCo V2 + Distillation Loss:

Our Distillation Loss Only:

3. Testing:

Results & Models

Training Logs

Acknowledgement

Contact

Owner

Zhiqiang Shen

[CVPR'22] Official PyTorch Implementation of Collaborative Transformers for Grounded Situation Recognition

Improving Deep Network Debuggability via Sparse Decision Layers

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Implementation of the HMAX model of vision in PyTorch

Focal and Global Knowledge Distillation for Detectors

Code release for Local Light Field Fusion at SIGGRAPH 2019

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

HarDNeXt: Official HarDNeXt repository

Implementations of the algorithms in the paper Approximative Algorithms for Multi-Marginal Optimal Transport and Free-Support Wasserstein Barycenters

gACSON software for visualization, processing and analysis of three-dimensional electron microscopy images

(SIGIR2020) “Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback’’

Keras-1D-NN-Classifier

This is the implementation of our work Deep Extreme Cut (DEXTR), for object segmentation from extreme points.

A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding his way.

Official Pytorch implementation of the paper: "Locally Shifted Attention With Early Global Integration"

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

2021-MICCAI-Progressively Normalized Self-Attention Network for Video Polyp Segmentation

Unofficial Implementation of MLP-Mixer, gMLP, resMLP, Vision Permutator, S2MLPv2, RaftMLP, ConvMLP, ConvMixer in Jittor and PyTorch.

SpiroMask: Measuring Lung Function Using Consumer-Grade Masks

Sequential GCN for Active Learning

S²-BNN (Self-supervised Binary Neural Networks Using Distillation Loss)