Self-Supervised Image Classification

37 papers with code • 2 benchmarks • 1 datasets

This is the task of image classification using representations learnt with self-supervised learning. Self-supervised methods generally involve a pretext task that is solved to learn a good representation and a loss function to learn with. One example of a loss function is an autoencoder based loss where the goal is reconstruction of an image pixel-by-pixel. A more popular recent example is a contrastive loss, which measure the similarity of sample pairs in a representation space, and where there can be a varying target instead of a fixed target to reconstruct (as in the case of autoencoders).

A common evaluation protocol is to train a linear classifier on top of (frozen) representations learnt by self-supervised methods. The leaderboards for the linear evaluation protocol can be found below. In practice, it is more common to fine-tune features on a downstream task. An alternative evaluation protocol therefore uses semi-supervised learning and finetunes on a % of the labels. The leaderboards for the finetuning protocol can be accessed here.

You may want to read some blog posts before reading the papers and checking the leaderboards:

There is also Yann LeCun's talk at AAAI-20 which you can watch here (35:00+).

( Image credit: A Simple Framework for Contrastive Learning of Visual Representations )

Datasets


Greatest papers with code

On Mutual Information Maximization for Representation Learning

google-research/google-research ICLR 2020

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data.

Representation Learning Self-Supervised Image Classification

XCiT: Cross-Covariance Image Transformers

rwightman/pytorch-image-models 17 Jun 2021

We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries.

Instance Segmentation Object Detection +2

ResMLP: Feedforward networks for image classification with data-efficient training

rwightman/pytorch-image-models 7 May 2021

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification.

Ranked #5 on Image Classification on ImageNet V2 (using extra training data)

Data Augmentation Fine-Grained Image Classification +3

Bootstrap your own latent: A new approach to self-supervised Learning

deepmind/deepmind-research 13 Jun 2020

From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.

Representation Learning Self-Supervised Image Classification +2

Emerging Properties in Self-Supervised Vision Transformers

lucidrains/vit-pytorch 29 Apr 2021

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).

Copy Detection Self-Supervised Image Classification +3

Colorful Image Colorization

richzhang/colorization 28 Mar 2016

We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result.

Colorization Self-Supervised Image Classification

Improved Baselines with Momentum Contrastive Learning

facebookresearch/moco 9 Mar 2020

Contrastive unsupervised learning has recently shown encouraging progress, e. g., in Momentum Contrast (MoCo) and SimCLR.

Contrastive Learning Data Augmentation +2