# On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning

arXiv: https://arxiv.org/abs/2208.05744 · HTML: https://mlsanity.com/paper/2208.05744/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 68 references that are in the map.
- First posted on arXiv 11 Aug 2022.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [How Does Batch Normalization Help Optimization?](https://mlsanity.com/paper/1805.11604/) (2018)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)

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

- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget](https://mlsanity.com/paper/2304.10520/) (2023)
- [Cross-view Masked Diffusion Transformers for Person Image Synthesis](https://mlsanity.com/paper/2402.01516/) (2024)
- [Learning from Multi-Perception Features for Real-Word Image Super-resolution](https://mlsanity.com/paper/2305.18547/) (2023)
- [MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation](https://mlsanity.com/paper/2410.02130/) (2024)
- [Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?](https://mlsanity.com/paper/2406.10743/) (2024)
- [Self-Supervised Visual Representation Learning via Residual Momentum](https://mlsanity.com/paper/2211.09861/) (2022)
- [Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head](https://mlsanity.com/paper/2302.10260/) (2023)
- [E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization](https://mlsanity.com/paper/2502.09164/) (2025)
- [A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers](https://mlsanity.com/paper/2602.21596/) (2026)

## Abstract (arXiv)

Exponential Moving Average (EMA or momentum) is widely used in modern self-supervised learning (SSL) approaches, such as MoCo, for enhancing performance. We demonstrate that such momentum can also be plugged into momentum-free SSL frameworks, such as SimCLR, for a performance boost. Despite its wide use as a fundamental component in modern SSL frameworks, the benefit caused by momentum is not well understood. We find that its success can be at least partly attributed to the stability effect. In the first attempt, we analyze how EMA affects each part of the encoder and reveal that the portion near the encoder's input plays an insignificant role while the latter parts have much more influence. By monitoring the gradient of the overall loss with respect to the output of each block in the encoder, we observe that the final layers tend to fluctuate much more than other layers during backpropagation, i.e. less stability. Interestingly, we show that using EMA to the final part of the SSL encoder, i.e. projector, instead of the whole deep network encoder can give comparable or preferable performance. Our proposed projector-only momentum helps maintain the benefit of EMA but avoids the double forward computation.