Self-Supervised Image Classification
85 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:
- Contrastive Self-Supervised Learning - Ankesh Anand
- The Illustrated Self-Supervised Learning - Amit Chaudhary
- Self-supervised learning and computer vision - Jeremy Howard
- Self-Supervised Representation Learning - Lilian Weng
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 )
Benchmarks
These leaderboards are used to track progress in Self-Supervised Image Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Self-Supervised Image Classification models and implementations
ImageNet
Latest papers with no code
Estimating Physical Information Consistency of Channel Data Augmentation for Remote Sensing Images
The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervised image classification.
Perceptual Group Tokenizer: Building Perception with Iterative Grouping
In this paper, we propose the Perceptual Group Tokenizer, a model that entirely relies on grouping operations to extract visual features and perform self-supervised representation learning, where a series of grouping operations are used to iteratively hypothesize the context for pixels or superpixels to refine feature representations.
DINO as a von Mises-Fisher mixture model
With this interpretation, DINO assumes equal precision for all components when the prototypes are also $L^2$-normalized.
Masked Reconstruction Contrastive Learning with Information Bottleneck Principle
In order to alleviate the discriminative information overfitting problem effectively, we employ the reconstruction task to regularize the discriminative task.
Relational Self-Supervised Learning
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Most notably, ReLICv2 is the first unsupervised representation learning method to consistently outperform the supervised baseline in a like-for-like comparison over a range of ResNet architectures.
Divide and Contrast: Self-supervised Learning from Uncurated Data
Self-supervised learning holds promise in leveraging large amounts of unlabeled data, however much of its progress has thus far been limited to highly curated pre-training data such as ImageNet.
Large-Scale Unsupervised Person Re-Identification with Contrastive Learning
In particular, most existing unsupervised and domain adaptation ReID methods utilize only the public datasets in their experiments, with labels removed.
Self-supervised Pre-training with Hard Examples Improves Visual Representations
Self-supervised pre-training (SSP) employs random image transformations to generate training data for visual representation learning.
A Pseudo-labelling Auto-Encoder for unsupervised image classification
In this paper, we introduce a unique variant of the denoising Auto-Encoder and combine it with the perceptual loss to classify images in an unsupervised manner.
