Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Related tags

Deep LearningDeCLIP
Overview

DeCLIP

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm.

Our paper is available in arxiv

Updates

** Our code, dataset and models will be relased soon**

Introduction

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) (Radfordet al., 2021) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite data-hungry and requires 400M image-text pairs for pre-training, thereby restricting its adoption. This work proposes a novel training paradigm, Data efficient CLIP (DeCLIP), to alleviate this limitation. We demonstrate that by carefully utilizing the widespread supervision among the image-text pairs, our DeCLIP can learn generic visual features more efficiently. Instead of using the single image-text contrastive supervision, we fully exploit data potential through the use of (1) self-supervision within each modality; (2) multi-view supervision across modalities; (3) nearest-neighbor supervision from other similar pairs. Benefiting from these intrinsic supervision, our DeCLIP-ResNet50 can achieve 60.4% zero-shot top1 accuracy on ImageNet, which is 0.8% above the CLIP-ResNet50 while using 7.1× fewer data. Our DeCLIP-ResNet50 outperforms its counterpart in 8 out of 11 visual datasets when transferred to downstream tasks. Moreover, Scaling up the model and computing also works well in our framework.

main_figure

Model

Our pretrain visual backbone model (w/o text encoder)

DeCLIP_r50 GoogleDriver.
DeCLIP_vitb32 GoogleDriver

Citing DeCLIP

@misc{li2021supervision,
      title={Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm}, 
      author={Yangguang Li and Feng Liang and Lichen Zhao and Yufeng Cui and Wanli Ouyang and Jing Shao and Fengwei Yu and Junjie Yan},
      year={2021},
      eprint={2110.05208},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Owner
Sense-GVT
Sense-GVT
DiSECt: Differentiable Simulator for Robotic Cutting

DiSECt: Differentiable Simulator for Robotic Cutting Website | Paper | Dataset | Video | Blog post DiSECt is a simulator for the cutting of deformable

NVIDIA Research Projects 73 Oct 29, 2022
Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!

Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation of the NeurIPS 2021 paper Alias-Free Generative Adversarial Net

Diego Porres 185 Dec 24, 2022
Shuffle Attention for MobileNetV3

SA-MobileNetV3 Shuffle Attention for MobileNetV3 Train Run the following command for train model on your own dataset: python train.py --dataset mnist

Sajjad Aemmi 36 Dec 28, 2022
This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

Project This repo has been populated by an initial template to help get you started. Please make sure to update the content to build a great experienc

Microsoft 674 Dec 26, 2022
Dark Finix: All in one hacking framework with almost 100 tools

Dark Finix - Hacking Framework. Dark Finix is a all in one hacking framework wit

Md. Nur habib 2 Feb 18, 2022
This is the repo for our work "Towards Persona-Based Empathetic Conversational Models" (EMNLP 2020)

Towards Persona-Based Empathetic Conversational Models (PEC) This is the repo for our work "Towards Persona-Based Empathetic Conversational Models" (E

Zhong Peixiang 35 Nov 17, 2022
The Instructed Glacier Model (IGM)

The Instructed Glacier Model (IGM) Overview The Instructed Glacier Model (IGM) simulates the ice dynamics, surface mass balance, and its coupling thro

27 Dec 16, 2022
A toolset for creating Qualtrics-based IAT experiments

Qualtrics IAT Tool A web app for generating the Implicit Association Test (IAT) running on Qualtrics Online Web App The app is hosted by Streamlit, a

0 Feb 12, 2022
3D-Reconstruction 基于深度学习方法的单目多视图三维重建

基于深度学习方法的单目多视图三维重建 Part I 三维重建 代码:Part1 技术文档:[Markdown] [PDF] 原始图像:Original Images 点云结果:Point Cloud Results-1

HMT_Curo 19 Dec 26, 2022
Code for the paper: Hierarchical Reinforcement Learning With Timed Subgoals, published at NeurIPS 2021

Hierarchical reinforcement learning with Timed Subgoals (HiTS) This repository contains code for reproducing experiments from our paper "Hierarchical

Autonomous Learning Group 21 Dec 03, 2022
My 1st place solution at Kaggle Hotel-ID 2021

1st place solution at Kaggle Hotel-ID My 1st place solution at Kaggle Hotel-ID to Combat Human Trafficking 2021. https://www.kaggle.com/c/hotel-id-202

Kohei Ozaki 18 Aug 19, 2022
Tgbox-bench - Simple TGBOX upload speed benchmark

TGBOX Benchmark This script will benchmark upload speed to TGBOX storage. Build

Non 1 Jan 09, 2022
This is the repository for The Machine Learning Workshops, published by AI DOJO

This is the repository for The Machine Learning Workshops, published by AI DOJO. It contains all the workshop's code with supporting project files necessary to work through the code.

AI Dojo 12 May 06, 2022
This repository is maintained for the scientific paper tittled " Study of keyword extraction techniques for Electric Double Layer Capacitor domain using text similarity indexes: An experimental analysis "

kwd-extraction-study This repository is maintained for the scientific paper tittled " Study of keyword extraction techniques for Electric Double Layer

ping 543f 1 Dec 05, 2022
Few-shot Neural Architecture Search

One-shot Neural Architecture Search uses a single supernet to approximate the performance each architecture. However, this performance estimation is super inaccurate because of co-adaption among oper

Yiyang Zhao 38 Oct 18, 2022
Multimodal Descriptions of Social Concepts: Automatic Modeling and Detection of (Highly Abstract) Social Concepts evoked by Art Images

MUSCO - Multimodal Descriptions of Social Concepts Automatic Modeling of (Highly Abstract) Social Concepts evoked by Art Images This project aims to i

0 Aug 22, 2021
Suite of 500 procedurally-generated NLP tasks to study language model adaptability

TaskBench500 The TaskBench500 dataset and code for generating tasks. Data The TaskBench dataset is available under wget http://web.mit.edu/bzl/www/Tas

Belinda Li 20 May 17, 2022
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

The first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitecture design and Training techniques towards diverse noises.

132 Dec 23, 2022
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

involution Official implementation of a neural operator as described in Involution: Inverting the Inherence of Convolution for Visual Recognition (CVP

Duo Li 1.3k Dec 28, 2022
HomeAssitant custom integration for dyson

HomeAssistant Custom Integration for Dyson This custom integration is still under development. This is a HA custom integration for dyson. There are se

Xiaonan Shen 232 Dec 31, 2022