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

Image Matching Evaluation

Baseline powergrid model for NY

A Python framework for developing parallelized Computational Fluid Dynamics software to solve the hyperbolic 2D Euler equations on distributed, multi-block structured grids.

An Inverse Kinematics library aiming performance and modularity

UnsupervisedR&R: Unsupervised Pointcloud Registration via Differentiable Rendering

Official Pytorch implementation of Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

A generalist algorithm for cell and nucleus segmentation.

Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

Auto-updating data to assist in investment to NEPSE

A simple pygame dino game which can also be trained and played by a NEAT KI

A clean and scalable template to kickstart your deep learning project 🚀 ⚡ 🔥

Shōgun

Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration

The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Code for sound field predictions in domains with impedance boundaries. Used for generating results from the paper

A variational Bayesian method for similarity learning in non-rigid image registration (CVPR 2022)

Pytorch implementation of TailCalibX : Feature Generation for Long-tail Classification

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

Minimal diffusion models - Minimal code and simple experiments to play with Denoising Diffusion Probabilistic Models (DDPMs)

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