# Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

arXiv: https://arxiv.org/abs/2403.15835 · HTML: https://mlsanity.com/paper/2403.15835/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 23 Mar 2024.

## Builds on (most cited first, 30 of 42)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://mlsanity.com/paper/2205.14401/) (2022)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers](https://mlsanity.com/paper/2106.12620/) (2021)
- [Scalable Vision Transformers with Hierarchical Pooling](https://mlsanity.com/paper/2103.10619/) (2021)
- [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021)
- [Unified Visual Transformer Compression](https://mlsanity.com/paper/2203.08243/) (2022)
- [Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space](https://mlsanity.com/paper/2201.00814/) (2022)
- [β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search](https://mlsanity.com/paper/2203.01665/) (2022)
- [BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search](https://mlsanity.com/paper/2103.12424/) (2021)
- [GLiT: Neural Architecture Search for Global and Local Image Transformer](https://mlsanity.com/paper/2107.02960/) (2021)
- [Searching the Search Space of Vision Transformer](https://mlsanity.com/paper/2111.14725/) (2021)

## Built on by (most cited first, 8 of 8)

- [KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems](https://mlsanity.com/paper/2510.12872/) (2025)
- [TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models](https://mlsanity.com/paper/2503.10501/) (2025)
- [Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy](https://mlsanity.com/paper/2410.09873/) (2024)
- [Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals](https://mlsanity.com/paper/2506.02281/) (2025)
- [CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers](https://mlsanity.com/paper/2602.05243/) (2026)
- [TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers](https://mlsanity.com/paper/2601.02437/) (2026)
- [Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation](https://mlsanity.com/paper/2508.16568/) (2025)
- [Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression](https://mlsanity.com/paper/2603.27383/) (2026)

## Abstract (arXiv)

Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint. Such a separate evaluation process induces the gap between importance and sparsity score distributions, thus causing high search costs for VTC. In this work, for the first time, we investigate how to integrate the evaluations of importance and sparsity scores into a single stage, searching the optimal subnets in an efficient manner. Specifically, we present OFB, a cost-efficient approach that simultaneously evaluates both importance and sparsity scores, termed Once for Both (OFB), for VTC. First, a bi-mask scheme is developed by entangling the importance score and the differentiable sparsity score to jointly determine the pruning potential (prunability) of each unit. Such a bi-mask search strategy is further used together with a proposed adaptive one-hot loss to realize the progressive-and-efficient search for the most important subnet. Finally, Progressive Masked Image Modeling (PMIM) is proposed to regularize the feature space to be more representative during the search process, which may be degraded by the dimension reduction. Extensive experiments demonstrate that OFB can achieve superior compression performance over state-of-the-art searching-based and pruning-based methods under various Vision Transformer architectures, meanwhile promoting search efficiency significantly, e.g., costing one GPU search day for the compression of DeiT-S on ImageNet-1K.