# Learning to See by Moving

arXiv: https://arxiv.org/abs/1505.01596 · HTML: https://mlsanity.com/paper/1505.01596/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2015.

## Built on by (most cited first, 30 of 102)

- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Efficient Visual Pretraining with Contrastive Detection](https://mlsanity.com/paper/2103.10957/) (2021)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective](https://mlsanity.com/paper/2103.17263/) (2021)
- [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://mlsanity.com/paper/2202.08360/) (2022)
- [Object discovery and representation networks](https://mlsanity.com/paper/2203.08777/) (2022)
- [Siamese Masked Autoencoders](https://mlsanity.com/paper/2305.14344/) (2023)
- [Advancing Radiograph Representation Learning with Masked Record Modeling](https://mlsanity.com/paper/2301.13155/) (2023)
- [Equivariant Contrastive Learning](https://mlsanity.com/paper/2111.00899/) (2021)
- [Self-supervised Video Transformer](https://mlsanity.com/paper/2112.01514/) (2021)
- [Learning Task Informed Abstractions](https://mlsanity.com/paper/2106.15612/) (2021)
- [SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations](https://mlsanity.com/paper/2112.04680/) (2021)
- [SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency](https://mlsanity.com/paper/2112.01001/) (2021)
- [Discovering Objects that Can Move](https://mlsanity.com/paper/2203.10159/) (2022)
- [Long-Short Temporal Contrastive Learning of Video Transformers](https://mlsanity.com/paper/2106.09212/) (2021)
- [Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video](https://mlsanity.com/paper/2310.08584/) (2023)
- [Contrasting Contrastive Self-Supervised Representation Learning Pipelines](https://mlsanity.com/paper/2103.14005/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2104.07917/) (2021)
- [Self-supervised Learning from 100 Million Medical Images](https://mlsanity.com/paper/2201.01283/) (2022)
- [MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis](https://mlsanity.com/paper/2207.10228/) (2022)
- [Jigsaw Clustering for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2104.00323/) (2021)
- [Scaling 4D Representations](https://mlsanity.com/paper/2412.15212/) (2024)
- [Exploring Set Similarity for Dense Self-supervised Representation Learning](https://mlsanity.com/paper/2107.08712/) (2021)
- [Self-Supervised Representation Learning from Flow Equivariance](https://mlsanity.com/paper/2101.06553/) (2021)
- [Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning](https://mlsanity.com/paper/2203.14333/) (2022)

## Abstract (arXiv)

The dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it possible to learn useful features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigate if the awareness of egomotion can be used as a supervisory signal for feature learning. As opposed to the knowledge of class labels, information about egomotion is freely available to mobile agents. We show that given the same number of training images, features learnt using egomotion as supervision compare favourably to features learnt using class-label as supervision on visual tasks of scene recognition, object recognition, visual odometry and keypoint matching.