DeepAI AI Chat
Log In Sign Up

A simple, efficient and scalable contrastive masked autoencoder for learning visual representations

by   Shlok Mishra, et al.
University of Maryland

We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the high-frequency components of an image. The combined approach results in a robust, scalable and simple-to-implement algorithm. The training process is symmetric, with 50 considerable efficiency improvement over prior contrastive learning methods. Extensive empirical studies demonstrate that CAN achieves strong downstream performance under both linear and finetuning evaluations on transfer learning and robustness tasks. CAN outperforms MAE and SimCLR when pre-training on ImageNet, but is especially useful for pre-training on larger uncurated datasets such as JFT-300M: for linear probe on ImageNet, CAN achieves 75.4 compared to 73.4 ImageNet of our ViT-L model is 86.1 for MAE. The overall FLOPs load of SimCLR is 70 models.


page 4

page 8

page 14

page 15

page 16

page 17


Denoising Diffusion Autoencoders are Unified Self-supervised Learners

Inspired by recent advances in diffusion models, which are reminiscent o...

Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

Contrastive learning has achieved great success in self-supervised visua...

Steerable Equivariant Representation Learning

Pre-trained deep image representations are useful for post-training task...

Masked Contrastive Representation Learning

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learni...

Masked Frequency Modeling for Self-Supervised Visual Pre-Training

We present Masked Frequency Modeling (MFM), a unified frequency-domain-b...

i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?

Masked image modeling (MIM) has been recognized as a strong and popular ...

Decoupled Contrastive Learning

Contrastive learning (CL) is one of the most successful paradigms for se...