# Convolutional Bypasses Are Better Vision Transformer Adapters

arXiv: https://arxiv.org/abs/2207.07039 · HTML: https://mlsanity.com/paper/2207.07039/

## Key facts

- Cited by 121 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 30 of 39)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [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)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)

## Built on by (most cited first, 30 of 121)

- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Visual Prompt Multi-Modal Tracking](https://mlsanity.com/paper/2303.10826/) (2023)
- [FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer](https://mlsanity.com/paper/2212.03145/) (2022)
- [SimDA: Simple Diffusion Adapter for Efficient Video Generation](https://mlsanity.com/paper/2308.09710/) (2023)
- [Review of Large Vision Models and Visual Prompt Engineering](https://mlsanity.com/paper/2307.00855/) (2023)
- [Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.08566/) (2023)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model](https://mlsanity.com/paper/2401.17868/) (2024)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning](https://mlsanity.com/paper/2212.03220/) (2022)
- [Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning](https://mlsanity.com/paper/2403.18886/) (2024)
- [Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition](https://mlsanity.com/paper/2402.14505/) (2024)
- [Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies](https://mlsanity.com/paper/2410.19878/) (2024)
- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy](https://mlsanity.com/paper/2307.16867/) (2023)
- [Dual-path Adaptation from Image to Video Transformers](https://mlsanity.com/paper/2303.09857/) (2023)
- [SAMAug: Point Prompt Augmentation for Segment Anything Model](https://mlsanity.com/paper/2307.01187/) (2023)
- [ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models](https://mlsanity.com/paper/2403.16187/) (2024)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Temporal Adaptive RGBT Tracking with Modality Prompt](https://mlsanity.com/paper/2401.01244/) (2024)
- [AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors](https://mlsanity.com/paper/2403.04697/) (2024)
- [Few-shot Adaptation of Multi-modal Foundation Models: A Survey](https://mlsanity.com/paper/2401.01736/) (2024)
- [Time-, Memory- and Parameter-Efficient Visual Adaptation](https://mlsanity.com/paper/2402.02887/) (2024)
- [MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection](https://mlsanity.com/paper/2404.08452/) (2024)
- [Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone](https://mlsanity.com/paper/2310.19859/) (2023)
- [Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation](https://mlsanity.com/paper/2403.11808/) (2024)
- [Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions](https://mlsanity.com/paper/2306.09729/) (2023)
- [Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval](https://mlsanity.com/paper/2308.12509/) (2023)
- [Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark](https://mlsanity.com/paper/2402.02242/) (2024)

## Abstract (arXiv)

The pretrain-then-finetune paradigm has been widely adopted in computer vision. But as the size of Vision Transformer (ViT) grows exponentially, the full finetuning becomes prohibitive in view of the heavier storage overhead. Motivated by parameter-efficient transfer learning (PETL) on language transformers, recent studies attempt to insert lightweight adaptation modules (e.g., adapter layers or prompt tokens) to pretrained ViT and only finetune these modules while the pretrained weights are frozen. However, these modules were originally proposed to finetune language models and did not take into account the prior knowledge specifically for visual tasks. In this paper, we propose to construct Convolutional Bypasses (Convpass) in ViT as adaptation modules, introducing only a small amount (less than 0.5% of model parameters) of trainable parameters to adapt the large ViT. Different from other PETL methods, Convpass benefits from the hard-coded inductive bias of convolutional layers and thus is more suitable for visual tasks, especially in the low-data regime. Experimental results on VTAB-1K benchmark and few-shot learning datasets show that Convpass outperforms current language-oriented adaptation modules, demonstrating the necessity to tailor vision-oriented adaptation modules for adapting vision models.