{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/introducing-routing-functions-to-vision","title":"Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks","arxiv_id":"2403.09377","date":"2024-03-14","proceeding":null,"authors":["Tingyu Qu","Tinne Tuytelaars","Marie-Francine Moens"],"abstract":"Mainstream parameter-efficient fine-tuning (PEFT) methods, such as LoRA or Adapter, project a model's hidden states to a lower dimension, allowing pre-trained models to adapt to new data through this low-rank bottleneck. However, PEFT tasks involving multiple modalities, like vision-language (VL) tasks, require not only adaptation to new data but also learning the relationship between different modalities. Targeting at VL PEFT tasks, we propose a family of operations, called routing functions, to enhance VL alignment in the low-rank bottlenecks. These feature routing functions adopt linear operations and do not introduce new trainable parameters. In-depth analyses are conducted to study their behavior. In various VL PEFT settings, the routing functions significantly improve performance of the original PEFT methods, achieving over 20\\% improvement on VQAv2 ($\\text{RoBERTa}_{\\text{large}}$+ViT-L/16) and 30\\% on COCO Captioning (GPT2-medium+ViT-L/16). Also when fine-tuning a pre-trained multimodal model such as CLIP-BART, we observe smaller but consistent improvements across a range of VL PEFT tasks. Our code is available at https://github.com/tingyu215/Routing_VLPEFT.","url_abs":"https://arxiv.org/abs/2403.09377v2","url_pdf":"https://arxiv.org/pdf/2403.09377v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"introducing-routing-functions-to-vision","repo_url":"https://github.com/tingyu215/routing_vlpeft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.09377","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}