# Time-, Memory- and Parameter-Efficient Visual Adaptation

arXiv: https://arxiv.org/abs/2402.02887 · HTML: https://mlsanity.com/paper/2402.02887/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 61 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 54)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark](https://mlsanity.com/paper/1910.04867/) (2019)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)

## Built on by (most cited first, 28 of 28)

- [R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding](https://mlsanity.com/paper/2404.00801/) (2024)
- [A Practitioner's Guide to Continual Multimodal Pretraining](https://mlsanity.com/paper/2408.14471/) (2024)
- [A Survey on Efficient Vision-Language Models](https://mlsanity.com/paper/2504.09724/) (2025)
- [SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition](https://mlsanity.com/paper/2502.16601/) (2025)
- [Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference](https://mlsanity.com/paper/2405.14700/) (2024)
- [M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension](https://mlsanity.com/paper/2407.01131/) (2024)
- [MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba](https://mlsanity.com/paper/2411.03855/) (2024)
- [EDTformer: An Efficient Decoder Transformer for Visual Place Recognition](https://mlsanity.com/paper/2412.00784/) (2024)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning](https://mlsanity.com/paper/2410.14633/) (2024)
- [Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era](https://mlsanity.com/paper/2511.06024/) (2025)
- [ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts](https://mlsanity.com/paper/2412.08341/) (2024)
- [PAE MobiLLM: Privacy-Aware and Efficient LLM Fine-Tuning on the Mobile Device via Additive Side-Tuning](https://mlsanity.com/paper/2507.01216/) (2025)
- [Towards Optimal Adapter Placement for Efficient Transfer Learning](https://mlsanity.com/paper/2410.15858/) (2024)
- [Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers](https://mlsanity.com/paper/2410.21815/) (2024)
- [Streaming Detection of Queried Event Start](https://mlsanity.com/paper/2412.03567/) (2024)
- [Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning](https://mlsanity.com/paper/2510.10022/) (2025)
- [ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads](https://mlsanity.com/paper/2506.03433/) (2025)
- [A Framework for Double-Blind Federated Adaptation of Foundation Models](https://mlsanity.com/paper/2502.01289/) (2025)
- [Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation](https://mlsanity.com/paper/2604.09088/) (2026)
- [S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain](https://mlsanity.com/paper/2605.08589/) (2026)
- [EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction](https://mlsanity.com/paper/2506.12015/) (2025)
- [Early Intervention for VFM-based Multimodal Medical Image Classification](https://mlsanity.com/paper/2603.17514/) (2026)
- [CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models](https://mlsanity.com/paper/2603.18545/) (2026)
- [MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning](https://mlsanity.com/paper/2605.04058/) (2026)
- [Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning](https://mlsanity.com/paper/2606.11682/) (2026)
- [Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation](https://mlsanity.com/paper/2606.20457/) (2026)
- [DERA: Detached Edge-Residual Adaptation for Prohibited item Detection](https://mlsanity.com/paper/2609.12411/) (2026)

## Abstract (arXiv)

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many parameters are trained. They, however, typically still require backpropagating gradients throughout the model, meaning that their training-time and -memory cost does not reduce as significantly. We propose an adaptation method which does not backpropagate gradients through the backbone. We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone. As a result, our method is efficient not only in terms of parameters, but also in training-time and memory usage. Our approach achieves state-of-the-art accuracy-parameter trade-offs on the popular VTAB benchmark, and we further show how we outperform prior works with respect to training-time and -memory usage too. We further demonstrate the training efficiency and scalability of our method by adapting a vision transformer backbone of 4 billion parameters for the computationally demanding task of video classification, without any intricate model parallelism. Here, we outperform a prior adaptor-based method which could only scale to a 1 billion parameter backbone, or fully-finetuning a smaller backbone, with the same GPU and less training time.