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

Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

Code, environments, and scripts for the paper: "How Private Is Your RL Policy? An Inverse RL Based Analysis Framework"

Multiview 3D object detection on MultiviewC dataset through moft3d.

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

This is the source code for generating the ASL-Skeleton3D and ASL-Phono datasets. Check out the README.md for more details.

Roach: End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Offical implementation for "Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation".

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)

An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax

ERISHA is a mulitilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker's voice for which no expressive speech corpus is available.

Contrastive Language-Image Pretraining

The NEOSSat is a dual-mission microsatellite designed to detect potentially hazardous Earth-orbit-crossing asteroids and track objects that reside in deep space

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

Implementation of ICCV 2021 oral paper -- A Novel Self-Supervised Learning for Gaussian Mixture Model

git《Commonsense Knowledge Base Completion with Structural and Semantic Context》(AAAI 2020) GitHub: [fig1]

Release of the ConditionalQA dataset

Official code of paper "PGT: A Progressive Method for Training Models on Long Videos" on CVPR2021

This repository contains project created during the Data Challenge module at London School of Hygiene & Tropical Medicine

Generate pixel-style avatars with python.

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