Pith. sign in

arXiv preprint arXiv:2112.09133 , year=

Masked Feature Prediction for Self-Supervised Visual Pre-Training , author= · 2021 · arXiv 2112.09133

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it
read on arXiv browse 3 citing papers

fields

cs.CV 3

years

2024 1 2023 1 2022 1

verdicts

ACCEPT 2 CONDITIONAL 1

representative citing papers

Demystifying CLIP Data

cs.CV · 2023-09-28 · accept · novelty 6.0

MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.

citing papers explorer

Showing 3 of 3 citing papers.

  • Revisiting Feature Prediction for Learning Visual Representations from Video cs.CV · 2024-02-15 · conditional · none · ref 108

    V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.

  • Demystifying CLIP Data cs.CV · 2023-09-28 · accept · none · ref 88

    MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.

  • CoCa: Contrastive Captioners are Image-Text Foundation Models cs.CV · 2022-05-04 · accept · none · ref 56

    CoCa unifies contrastive and generative pretraining in one image-text model to reach 86.3% zero-shot ImageNet accuracy and new state-of-the-art results on multiple downstream benchmarks.