# Self-Supervised Representation Learning via Neighborhood-Relational Encoding

arXiv: https://arxiv.org/abs/1908.10455 · HTML: https://mlsanity.com/paper/1908.10455/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [Semantic Segmentation of Remote Sensing Images with Sparse Annotations](https://mlsanity.com/paper/2101.03492/) (2021)
- [Self-Supervised Euphemism Detection and Identification for Content Moderation](https://mlsanity.com/paper/2103.16808/) (2021)
- [Self-Supervised Longitudinal Neighbourhood Embedding](https://mlsanity.com/paper/2103.03840/) (2021)
- [CoCon: Cooperative-Contrastive Learning](https://mlsanity.com/paper/2104.14764/) (2021)
- [Image/Video Deep Anomaly Detection: A Survey](https://mlsanity.com/paper/2103.01739/) (2021)
- [Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning](https://mlsanity.com/paper/2408.09676/) (2024)
- [Adaptive-Gravity: A Defense Against Adversarial Samples](https://mlsanity.com/paper/2204.03694/) (2022)
- [CSSL-RHA: Contrastive Self-Supervised Learning for Robust Handwriting Authentication](https://mlsanity.com/paper/2307.11100/) (2023)
- [Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagery](https://mlsanity.com/paper/2411.18475/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visual data, mainly to be able to reconstruct the data from a latent space. They often neglected the relation among the samples, which can serve as an important metric for self-supervision. Different from the previous work, NRE aims at preserving the local neighborhood structure on the data manifold. Therefore, it is less sensitive to outliers. We integrate our NRE component with an encoder-decoder structure for learning to represent samples considering their local neighborhood information. Such discriminative and unsupervised representation learning scheme is adaptable to different computer vision tasks due to its independence from intense annotation requirements. We evaluate our proposed method for different tasks, including classification, detection, and segmentation based on the learned latent representations. In addition, we adopt the auto-encoding capability of our proposed method for applications like defense against adversarial example attacks and video anomaly detection. Results confirm the performance of our method is better or at least comparable with the state-of-the-art for each specific application, but with a generic and self-supervised approach.