Self-Supervised Learning

Barlow Twins

Introduced by Zbontar et al. in Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Barlow Twins is a self-supervised learning method that applies redundancy-reduction — a principle first proposed in neuroscience — to self supervised learning. The objective function measures the cross-correlation matrix between the embeddings of two identical networks fed with distorted versions of a batch of samples, and tries to make this matrix close to the identity. This causes the embedding vectors of distorted version of a sample to be similar, while minimizing the redundancy between the components of these vectors. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. Intriguingly it benefits from very high-dimensional output vectors.

Source: Barlow Twins: Self-Supervised Learning via Redundancy Reduction


Paper Code Results Date Stars


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign