# Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation

arXiv: https://arxiv.org/abs/2310.07265 · HTML: https://mlsanity.com/paper/2310.07265/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 68 of its 82 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 68)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)

## Built on by (most cited first, 18 of 18)

- [Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation](https://mlsanity.com/paper/2403.12505/) (2024)
- [Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities](https://mlsanity.com/paper/2407.11351/) (2024)
- [360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes](https://mlsanity.com/paper/2404.16501/) (2024)
- [The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2504.10686/) (2025)
- [The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2604.03198/) (2026)
- [Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?](https://mlsanity.com/paper/2505.11907/) (2025)
- [Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation](https://mlsanity.com/paper/2407.11344/) (2024)
- [MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection](https://mlsanity.com/paper/2412.16876/) (2024)
- [Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization](https://mlsanity.com/paper/2505.06635/) (2025)
- [Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation](https://mlsanity.com/paper/2501.08885/) (2025)
- [Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025](https://mlsanity.com/paper/2506.05856/) (2025)
- [Context-Aware Semantic Segmentation: Enhancing Pixel-Level Understanding with Large Language Models for Advanced Vision Applications](https://mlsanity.com/paper/2503.19276/) (2025)
- [Split Matching for Inductive Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2505.05023/) (2025)
- [EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentation](https://mlsanity.com/paper/2505.14014/) (2025)
- [Architectural Insights into Knowledge Distillation for Object Detection: A Comprehensive Review](https://mlsanity.com/paper/2508.03317/) (2025)
- [Towards Customized Knowledge Distillation for Chip-Level Dense Image Predictions](https://mlsanity.com/paper/2401.13174/) (2024)
- [SARTM: Segment Any RGB Thermal Model with Language aided Distillation](https://mlsanity.com/paper/2505.01950/) (2025)
- [Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2506.22032/) (2025)

## Abstract (arXiv)

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the completely different characteristics of ViT and CNN and the long-existing capacity gap between teacher and student models in Knowledge Distillation (KD), directly transferring the cross-model knowledge is non-trivial. To this end, we subtly leverage the visual and linguistic-compatible feature character of ViT (i.e., student), and its capacity gap with the CNN (i.e., teacher) and propose a novel CNN-to-ViT KD framework, dubbed C2VKD. Importantly, as the teacher's features are heterogeneous to those of the student, we first propose a novel visual-linguistic feature distillation (VLFD) module that explores efficient KD among the aligned visual and linguistic-compatible representations. Moreover, due to the large capacity gap between the teacher and student and the inevitable prediction errors of the teacher, we then propose a pixel-wise decoupled distillation (PDD) module to supervise the student under the combination of labels and teacher's predictions from the decoupled target and non-target classes. Experiments on three semantic segmentation benchmark datasets consistently show that the increment of mIoU of our method is over 200% of the SoTA KD methods