Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning

• URL: http://arxiv.org/abs/2606.11682v1
• Date: Wed, 10 Jun 2026 05:52:12 GMT
• Title: Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning
• Abstract summary: TI-Adapter is a modality-specific adapter-based fine-tuning framework for efficient multimodal adaptation.<n>Experiments show TI-Adapter achieves competitive or better predictive performance than full fine-tuning.
• Score: 0.40611352512781873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tabular-image multimodal learning aims to improve predictive modeling by jointly using structured tabular attributes and visual data. Although pretrained encoders provide strong modality-specific representations, full fine-tuning can be computationally expensive, while keeping encoders frozen may limit task-specific adaptation. We propose the Tabular-Image Adapter (TI-Adapter), a modality-specific adapter-based fine-tuning framework for efficient multimodal adaptation. TI-Adapter freezes the pretrained tabular encoder and learns an adapter after the extracted tabular embedding, while adapting the image branch with embedding-level and bottleneck-level adapters instead of full fine-tuning. Experiments on 20 tabular-image datasets show that TI-Adapter achieves competitive or better predictive performance than full fine-tuning while using substantially fewer trainable parameters. Ablation studies further demonstrate the importance of adapter placement for balancing performance and practical efficiency.

Related papers

• Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers [13.97407382426689]
  We introduce HyperAdapter, a hypergraph-based adapter architecture that enables structured, group-aware adaptation through soft token routing.<n>Experiments across diverse visual benchmarks demonstrate that structured hyperedge adaptation consistently outperforms strong PEFT baselines.
  arXiv  Detail & Related papers  (2026-06-21T08:09:08Z)
• DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models [103.18486625853099]
  DEFT, Decompositional Efficient Fine-Tuning, adapts a pre-trained weight matrix by decomposing its update into two components.<n>We conduct experiments on the Dreambooth and Dreambench Plus datasets for personalization, the InsDet dataset for object and scene adaptation, and the VisualCloze dataset for a universal image generation framework.
  arXiv  Detail & Related papers  (2025-09-26T18:01:15Z)
• iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation [15.97351561456467]
  In this paper, we propose a novel PEFT approach, input-Conditioned transFormer, termed iConFormer.<n>We introduce an input-Conditioned Network (iCoN) in the dynamic adapter that enables instance-level feature transformation.<n>To be specific, iCoN generates channel-wise convolutional kernels for each feature and transform it using adaptive convolution process to effectively capture task-specific and fine-grained details tailor to downstream tasks.
  arXiv  Detail & Related papers  (2024-09-04T16:06:23Z)
• Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation [67.13876021157887]
  Dynamic Tuning (DyT) is a novel approach to improve both parameter and inference efficiency for ViT adaptation. DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.
  arXiv  Detail & Related papers  (2024-03-18T14:05:52Z)
• Efficient Adapter Tuning of Pre-trained Speech Models for Automatic Speaker Verification [38.20393847192532]
  Self-supervised speech models have shown impressive performance on various downstream speech tasks. fine-tuning becomes practically unfeasible due to heavy computation and storage overhead. We propose an effective adapter framework designed for adapting self-supervised speech models to the speaker verification task.
  arXiv  Detail & Related papers  (2024-03-01T05:32:14Z)
• MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning [20.68925288222065]
  Mixture of Sparse Adapters, or MoSA, is a novel Adapter Tuning method. MoSA can achieve significantly better performance than standard without any additional computational storage overhead. MoSA consistently outperforms other Adapter Tuning methods as well as other baselines by a large margin.
  arXiv  Detail & Related papers  (2023-12-05T17:50:55Z)
• MerA: Merging Pretrained Adapters For Few-Shot Learning [71.44422347502409]
  We propose textbftextttMerging Pretrained Adapters (MerA) that efficiently incorporates pretrained adapters to a single model through model fusion. Experiments on two PLMs demonstrate that MerA substantial improvements compared to both single adapters and AdapterFusion.
  arXiv  Detail & Related papers  (2023-08-30T12:10:17Z)
• Adaptable Adapters [74.65986170056945]
  State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adaptable adapters contain different activation functions for different layers and different input data. We show that adaptable adapters achieve on-par performances with the standard adapter architecture.
  arXiv  Detail & Related papers  (2022-05-03T14:59:27Z)
• AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks [55.705355299065474]
  Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this study, AdapterBias, a surprisingly simple yet effective adapter architecture, is proposed.
  arXiv  Detail & Related papers  (2022-04-30T16:49:41Z)
• Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations [61.95114821573875]
  We introduce Plug-In Inversion, which relies on a simple set of augmentations and does not require excessive hyper- parameter tuning. We illustrate the practicality of our approach by inverting Vision Transformers (ViTs) and Multi-Layer Perceptrons (MLPs) trained on the ImageNet dataset.
  arXiv  Detail & Related papers  (2022-01-31T02:12:45Z)
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling [78.62723847797382]
  We propose textbfTraining-Free CLtextbfIP-textbfAdapter (textbfTip-Adapter), which not only inherits CLIP's training-free advantage but also performs comparably or even better than CLIP-Adapter. We conduct extensive experiments of few-shot classification on ImageNet and other 10 datasets to demonstrate the superiority of proposed Tip-Adapter.
  arXiv  Detail & Related papers  (2021-11-06T18:09:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.