# The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

arXiv: https://arxiv.org/abs/2012.06908 · HTML: https://mlsanity.com/paper/2012.06908/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2020.

## Built on by (most cited first, 30 of 91)

- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [A Unified Lottery Ticket Hypothesis for Graph Neural Networks](https://mlsanity.com/paper/2102.06790/) (2021)
- [The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training](https://mlsanity.com/paper/2202.02643/) (2022)
- [Sparse Training via Boosting Pruning Plasticity with Neuroregeneration](https://mlsanity.com/paper/2106.10404/) (2021)
- [Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization](https://mlsanity.com/paper/2105.12002/) (2021)
- [Advancing Model Pruning via Bi-level Optimization](https://mlsanity.com/paper/2210.04092/) (2022)
- [Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better](https://mlsanity.com/paper/2112.09824/) (2021)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?](https://mlsanity.com/paper/2107.00166/) (2021)
- [How Well Do Sparse Imagenet Models Transfer?](https://mlsanity.com/paper/2111.13445/) (2021)
- [Dynamic Sparse Training for Deep Reinforcement Learning](https://mlsanity.com/paper/2106.04217/) (2021)
- [Playing Lottery Tickets with Vision and Language](https://mlsanity.com/paper/2104.11832/) (2021)
- [Efficient Lottery Ticket Finding: Less Data is More](https://mlsanity.com/paper/2106.03225/) (2021)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Recent Advances on Neural Network Pruning at Initialization](https://mlsanity.com/paper/2103.06460/) (2021)
- [Sparsity Winning Twice: Better Robust Generalization from More Efficient Training](https://mlsanity.com/paper/2202.09844/) (2022)
- [GANs Can Play Lottery Tickets Too](https://mlsanity.com/paper/2106.00134/) (2021)
- [XPrompt: Exploring the Extreme of Prompt Tuning](https://mlsanity.com/paper/2210.04457/) (2022)
- [Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets](https://mlsanity.com/paper/2202.04736/) (2022)
- [Training Your Sparse Neural Network Better with Any Mask](https://mlsanity.com/paper/2206.12755/) (2022)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers](https://mlsanity.com/paper/2302.02596/) (2023)
- [On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.01648/) (2021)
- [A Survey of Lottery Ticket Hypothesis](https://mlsanity.com/paper/2403.04861/) (2024)
- [The Elastic Lottery Ticket Hypothesis](https://mlsanity.com/paper/2103.16547/) (2021)
- [Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective](https://mlsanity.com/paper/2312.01397/) (2023)
- [Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models](https://mlsanity.com/paper/2306.10460/) (2023)

## Abstract (arXiv)

The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervised pre-training such as simCLR and MoCo. Pre-trained weights often boost a wide range of downstream tasks including classification, detection, and segmentation. Latest studies suggest that pre-training benefits from gigantic model capacity. We are hereby curious and ask: after pre-training, does a pre-trained model indeed have to stay large for its downstream transferability? In this paper, we examine supervised and self-supervised pre-trained models through the lens of the lottery ticket hypothesis (LTH). LTH identifies highly sparse matching subnetworks that can be trained in isolation from (nearly) scratch yet still reach the full models' performance. We extend the scope of LTH and question whether matching subnetworks still exist in pre-trained computer vision models, that enjoy the same downstream transfer performance. Our extensive experiments convey an overall positive message: from all pre-trained weights obtained by ImageNet classification, simCLR, and MoCo, we are consistently able to locate such matching subnetworks at 59.04% to 96.48% sparsity that transfer universally to multiple downstream tasks, whose performance see no degradation compared to using full pre-trained weights. Further analyses reveal that subnetworks found from different pre-training tend to yield diverse mask structures and perturbation sensitivities. We conclude that the core LTH observations remain generally relevant in the pre-training paradigm of computer vision, but more delicate discussions are needed in some cases. Codes and pre-trained models will be made available at: https://github.com/VITA-Group/CV_LTH_Pre-training.