Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning
Not on the map. Why?
Abstract (arXiv)
Existing architectures of multi-domain learning have two types of adapters: shared LoRA for all domains and domain-specific LoRA for each particular domain. However, it remains unclear whether this structure effectively captures domain-specific information. In this paper, we propose a method that ensures that shared and domain-specific LoRAs exist in different subspaces; specifically, the column and left null subspaces of the pre-trained weights. We apply the proposed method to action recognition with three datasets (UCF101, Kinetics400, and HMDB51) and demonstrate its effectiveness in some cases along with the analysis of the dimensions of LoRA weights.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 5 Aug 2025.
Builds on
32 of 43 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
- 2017The Kinetics Human Action Video Datasetcited by 1,909
- 2017A Survey on Multi-Task Learningcited by 840
- 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
- 2021ImageNet-21K Pretraining for the Massescited by 613
20 more
- 2017Learning multiple visual domains with residual adapterscited by 557
- 2022Multimodal Learning with Transformers: A Surveycited by 400
- 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
- 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 320
- 2021Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworkscited by 284
- 2018Human Action Recognition and Prediction: A Surveycited by 227
- 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
- 2018Efficient parametrization of multi-domain deep neural networkscited by 168
- 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
- 2021Simple multi-dataset detectioncited by 127
- 2024Large Multimodal Agents: A Surveycited by 105
- 2022Video Transformers: A Surveycited by 63
- 2023VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understandingcited by 62
- 2021PolyViT: Co-training Vision Transformers on Images, Videos and Audiocited by 58
- 2022Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Taskscited by 52
- 2024MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learningcited by 44
- 2019Mimetics: Towards Understanding Human Actions Out of Contextcited by 32
- 2022Vision Transformers for Action Recognition: A Surveycited by 25
- 2019Efficient Multi-Domain Network Learning by Covariance Normalizationcited by 16
- 2022Multi-dataset Training of Transformers for Robust Action Recognitioncited by 10
Built on by
Citing papers per year: 2026: 1.
1 paper.