# AttentionLite: Towards Efficient Self-Attention Models for Vision

arXiv: https://arxiv.org/abs/2101.05216 · HTML: https://mlsanity.com/paper/2101.05216/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

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

- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise](https://mlsanity.com/paper/2110.11417/) (2021)
- [Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference](https://mlsanity.com/paper/2301.09254/) (2023)
- [Pipeline Parallelism for Inference on Heterogeneous Edge Computing](https://mlsanity.com/paper/2110.14895/) (2021)
- [Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge](https://mlsanity.com/paper/2208.13092/) (2022)
- [ViTA: A Vision Transformer Inference Accelerator for Edge Applications](https://mlsanity.com/paper/2302.09108/) (2023)
- [Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference](https://mlsanity.com/paper/2304.13274/) (2023)
- [Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural networks: from Algorithms to Technology](https://mlsanity.com/paper/2312.01213/) (2023)
- [Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models](https://mlsanity.com/paper/2110.08536/) (2021)
- [A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness](https://mlsanity.com/paper/2204.00426/) (2022)

## Abstract (arXiv)

We propose a novel framework for producing a class of parameter and compute efficient models called AttentionLitesuitable for resource-constrained applications. Prior work has primarily focused on optimizing models either via knowledge distillation or pruning. In addition to fusing these two mechanisms, our joint optimization framework also leverages recent advances in self-attention as a substitute for convolutions. We can simultaneously distill knowledge from a compute-heavy teacher while also pruning the student model in a single pass of training thereby reducing training and fine-tuning times considerably. We evaluate the merits of our proposed approach on the CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets. Not only do our AttentionLite models significantly outperform their unoptimized counterparts in accuracy, we find that in some cases, that they perform almost as well as their compute-heavy teachers while consuming only a fraction of the parameters and FLOPs. Concretely, AttentionLite models can achieve upto30x parameter efficiency and 2x computation efficiency with no significant accuracy drop compared to their teacher.