# When Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High Compression

arXiv: https://arxiv.org/abs/2607.02237 · HTML: https://mlsanity.com/paper/2607.02237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Token pruning and merging for ViTs, one of 12 directions in Efficient LLM inference and serving.
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- Efficient LLM inference and serving / [Token pruning and merging for ViTs](https://mlsanity.com/inference/token-pruning-and-merging-for-vits/)

## Builds on (most cited first, 30 of 34)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [What Do Compressed Deep Neural Networks Forget?](https://mlsanity.com/paper/1911.05248/) (2019)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [Token Fusion: Bridging the Gap between Token Pruning and Token Merging](https://mlsanity.com/paper/2312.01026/) (2023)
- [Benchmarking the Robustness of Semantic Segmentation Models](https://mlsanity.com/paper/1908.05005/) (2019)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [DiffRate : Differentiable Compression Rate for Efficient Vision Transformers](https://mlsanity.com/paper/2305.17997/) (2023)
- [Global Vision Transformer Pruning with Hessian-Aware Saliency](https://mlsanity.com/paper/2110.04869/) (2021)
- [Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation](https://mlsanity.com/paper/2308.01045/) (2023)
- [Which Tokens to Use? Investigating Token Reduction in Vision Transformers](https://mlsanity.com/paper/2308.04657/) (2023)
- [UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers](https://mlsanity.com/paper/2301.13741/) (2023)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism](https://mlsanity.com/paper/2303.02387/) (2023)
- [ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2406.09936/) (2024)
- [Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers](https://mlsanity.com/paper/2306.02095/) (2023)

## Abstract (arXiv)

Vision Transformers (ViTs) are strong backbones for semantic segmentation, but their computational cost limits deployment. Recent token compression methods for efficient transformer-based segmentation reduce this cost by decreasing the number of tokens. However, existing evaluations primarily focus on low-to-moderate compression, leaving their behavior under aggressive compression and corrupted inputs unclear. Meanwhile, structural pruning provides an orthogonal route to efficiency by removing redundant components in the ViT architecture, but is rarely compared to token compression under a unified protocol. To bridge this gap, we benchmark representative token compression and structural pruning methods for ViT-based semantic segmentation under matched FLOPs on ADE20K and Cityscapes, together with their common-corruption variants ADE20K-C and Cityscapes-C. Our results reveal a consistent trend on both clean and corrupted inputs: token compression is highly effective at mild reductions but degrades sharply when compression becomes severe, consistent with substantial information loss from overly aggressive token reduction. In contrast, structural pruning exhibits a smoother degradation curve and is more stable at high compression. Motivated by these findings, we study a prune-then-merge pipeline that applies moderate token compression on top of a moderately pruned backbone. At comparable FLOPs, this combined strategy consistently achieves a better accuracy-robustness trade-off at high compression, offering a practical recipe for deployment-oriented ViT segmentation. Code is available at https://github.com/phatnguyencs/vit-seg-compression.