# The Lottery Ticket Hypothesis for Object Recognition

arXiv: https://arxiv.org/abs/2012.04643 · HTML: https://mlsanity.com/paper/2012.04643/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 30 of 34)

- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023)
- [Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization](https://mlsanity.com/paper/2105.12002/) (2021)
- [Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?](https://mlsanity.com/paper/2107.00166/) (2021)
- [NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling](https://mlsanity.com/paper/2212.14593/) (2022)
- [How Well Do Sparse Imagenet Models Transfer?](https://mlsanity.com/paper/2111.13445/) (2021)
- [Playing Lottery Tickets with Vision and Language](https://mlsanity.com/paper/2104.11832/) (2021)
- [Rare Gems: Finding Lottery Tickets at Initialization](https://mlsanity.com/paper/2202.12002/) (2022)
- [SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations](https://mlsanity.com/paper/2309.15848/) (2023)
- [Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks](https://mlsanity.com/paper/2110.14068/) (2021)
- [Exploring Lottery Ticket Hypothesis in Spiking Neural Networks](https://mlsanity.com/paper/2207.01382/) (2022)
- [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)
- [Dynamic Sparse Network for Time Series Classification: Learning What to "see''](https://mlsanity.com/paper/2212.09840/) (2022)
- [Knowledge Evolution in Neural Networks](https://mlsanity.com/paper/2103.05152/) (2021)
- [A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications](https://mlsanity.com/paper/2106.09259/) (2021)
- [Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey](https://mlsanity.com/paper/2205.08099/) (2022)
- [Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction](https://mlsanity.com/paper/2406.04934/) (2024)
- [The rise of the lottery heroes: why zero-shot pruning is hard](https://mlsanity.com/paper/2202.12400/) (2022)
- [LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification](https://mlsanity.com/paper/2204.02965/) (2022)
- [Data Level Lottery Ticket Hypothesis for Vision Transformers](https://mlsanity.com/paper/2211.01484/) (2022)
- [Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket](https://mlsanity.com/paper/2308.02916/) (2023)
- [How much pre-training is enough to discover a good subnetwork?](https://mlsanity.com/paper/2108.00259/) (2021)
- [Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation](https://mlsanity.com/paper/2410.23693/) (2024)
- [Membership Inference Attacks on Lottery Ticket Networks](https://mlsanity.com/paper/2108.03506/) (2021)
- [Probabilistic Modeling: Proving the Lottery Ticket Hypothesis in Spiking Neural Network](https://mlsanity.com/paper/2305.12148/) (2023)
- [3D Point Cloud Network Pruning: When Some Weights Do not Matter](https://mlsanity.com/paper/2408.14601/) (2024)
- [Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning](https://mlsanity.com/paper/2305.14852/) (2023)
- [Playing Lottery Tickets in Style Transfer Models](https://mlsanity.com/paper/2203.13802/) (2022)
- [Reconstruction Task Finds Universal Winning Tickets](https://mlsanity.com/paper/2202.11484/) (2022)

## Abstract (arXiv)

Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory footprints. This makes it exceedingly difficult to deploy these systems on low power embedded devices. Hence, the importance of decreasing the storage requirements and the amount of computation in such models is paramount. The recently proposed Lottery Ticket Hypothesis (LTH) states that deep neural networks trained on large datasets contain smaller subnetworks that achieve on par performance as the dense networks. In this work, we perform the first empirical study investigating LTH for model pruning in the context of object detection, instance segmentation, and keypoint estimation. Our studies reveal that lottery tickets obtained from ImageNet pretraining do not transfer well to the downstream tasks. We provide guidance on how to find lottery tickets with up to 80% overall sparsity on different sub-tasks without incurring any drop in the performance. Finally, we analyse the behavior of trained tickets with respect to various task attributes such as object size, frequency, and difficulty of detection.