Self-supervised representation learning on manifolds

2021-03-08 · ICLR Workshop GTRL 2021 5 · Eric O Korman

We explore the use of a topological manifold, represented as a collection of charts, as the target space of neural network based representation learning tasks. This is achieved by a simple adjustment to the output of an encoder's network architecture plus the addition of a maximal mean discrepancy based loss function for regularization. Most algorithms in representation learning are easily adaptable to our framework and we demonstrate its effectiveness by adjusting SimCLR to have a manifold encoding space. Our experiments show that we obtain a substantial performance boost over the baseline for low dimensional encodings. Code for reproducing experiments is provided at https://github.com/ekorman/neurve.

📄 PDF Abstract BibTeX

Code (1)

ekorman/neurve 공식 구현 pytorch

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음

Batch Normalization 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Residual Connection 설명 없음

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Average Pooling 설명 없음

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Contrastive Self-Supervised Learning As Neural Manifold Packing

2025-06-16 · Guanming Zhang, David J. Heeger, Stefano Martiniani

Contrastive self-supervised learning based on point-wise comparisons has been widely studied for vision tasks. In the visual cortex of the brain, neuronal responses to distinct stimulus classes are organized into geometr…

Contrastive Learning Linear evaluation Representation Learning Self-Supervised Learning

On Linear Separation Capacity of Self-Supervised Representation Learning

2023-10-29 · Shulei Wang

Recent advances in self-supervised learning have highlighted the efficacy of data augmentation in learning data representation from unlabeled data. Training a linear model atop these enhanced representations can yield an…

Data Augmentation Representation Learning Self-Supervised Learning

Robust Self-Supervised Convolutional Neural Network for Subspace Clustering and Classification

2020-04-03 · Dario Sitnik, Ivica Kopriva

Insufficient capability of existing subspace clustering methods to handle data coming from nonlinear manifolds, data corruptions, and out-of-sample data hinders their applicability to address real-world clustering and cl…

Clustering General Classification

Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections

2025-10-26 · Berken Utku Demirel, Christian Holz arxiv

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data. Most SSL approaches rely on strong, well-established, handcrafted data augmentations to generate divers…

Self-Supervised Learning Representation Learning

A Neural Network for Semi-Supervised Learning on Manifolds

2019-08-21 · Alexander Genkin, Anirvan M. Sengupta, Dmitri Chklovskii

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online settin…