Browse SoTA > Computer Vision > Image Classification > Self-Supervised Image Classification

Self-Supervised Image Classification

17 papers with code · Computer Vision

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 )

Leaderboards

Greatest papers with code

On Mutual Information Maximization for Representation Learning

ICLR 2020 google-research/google-research

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

Colorful Image Colorization

28 Mar 2016richzhang/colorization

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

9 Mar 2020facebookresearch/moco

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

CONTRASTIVE LEARNING DATA AUGMENTATION REPRESENTATION LEARNING SELF-SUPERVISED IMAGE CLASSIFICATION

Big Self-Supervised Models are Strong Semi-Supervised Learners

17 Jun 2020google-research/simclr

The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2 (a modification of SimCLR), supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge.

SELF-SUPERVISED IMAGE CLASSIFICATION SEMI-SUPERVISED IMAGE CLASSIFICATION

Contrastive Multiview Coding

ICLR 2020 HobbitLong/CMC

We analyze key properties of the approach that make it work, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views we learn from, the better the resulting representation captures underlying scene semantics.

CONTRASTIVE LEARNING OBJECT CLASSIFICATION SELF-SUPERVISED ACTION RECOGNITION SELF-SUPERVISED IMAGE CLASSIFICATION

What makes for good views for contrastive learning

20 May 2020HobbitLong/PyContrast

Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning.

CONTRASTIVE LEARNING DATA AUGMENTATION INSTANCE SEGMENTATION OBJECT DETECTION REPRESENTATION LEARNING SELF-SUPERVISED IMAGE CLASSIFICATION SEMANTIC SEGMENTATION

Self-Supervised Learning of Pretext-Invariant Representations

CVPR 2020 HobbitLong/PyContrast

The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images.

OBJECT DETECTION REPRESENTATION LEARNING SELF-SUPERVISED IMAGE CLASSIFICATION SELF-SUPERVISED LEARNING SEMI-SUPERVISED IMAGE CLASSIFICATION

Unsupervised Feature Learning via Non-Parametric Instance Discrimination

CVPR 2018 HobbitLong/PyContrast

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.

OBJECT DETECTION SELF-SUPERVISED IMAGE CLASSIFICATION SEMI-SUPERVISED IMAGE CLASSIFICATION