Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.10451 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917401234243584 |
|---|---|
| author | Poudel, Sanjaya Kunwor, Nikita Simkhada, Raj Munir, Mustafa Dhakal, Manish Poudel, Khem |
| author_facet | Poudel, Sanjaya Kunwor, Nikita Simkhada, Raj Munir, Mustafa Dhakal, Manish Poudel, Khem |
| contents | Despite recent advancements in the field of medical image analysis with the use of pretrained foundation models, the issue of distribution shifts between cross-source images largely remains adamant. To circumvent that issue, investigators generally train a separate model for each source. However, this method becomes expensive when we fully fine-tune pretrained large models for a single dataset, as we must store multiple copies of those models. Thus, in this work, we propose using a low-rank adaptation (LoRA) module for fine-tuning downstream classification tasks. LoRAs learn lightweight task-specific low-rank matrices that perturb pretrained weights to optimize those downstream tasks. For gastrointestinal tract diseases, they exhibit significantly better results than end-to-end finetuning with improved parameter efficiency. Code is available at: github.com/sanjay931/peft-gi-recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10451 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Parameter Efficient Fine-tuning for Domain-specific Gastrointestinal Disease Recognition Poudel, Sanjaya Kunwor, Nikita Simkhada, Raj Munir, Mustafa Dhakal, Manish Poudel, Khem Computer Vision and Pattern Recognition Despite recent advancements in the field of medical image analysis with the use of pretrained foundation models, the issue of distribution shifts between cross-source images largely remains adamant. To circumvent that issue, investigators generally train a separate model for each source. However, this method becomes expensive when we fully fine-tune pretrained large models for a single dataset, as we must store multiple copies of those models. Thus, in this work, we propose using a low-rank adaptation (LoRA) module for fine-tuning downstream classification tasks. LoRAs learn lightweight task-specific low-rank matrices that perturb pretrained weights to optimize those downstream tasks. For gastrointestinal tract diseases, they exhibit significantly better results than end-to-end finetuning with improved parameter efficiency. Code is available at: github.com/sanjay931/peft-gi-recognition. |
| title | Parameter Efficient Fine-tuning for Domain-specific Gastrointestinal Disease Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10451 |