Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters

• URL: http://arxiv.org/abs/2603.18101v1
• Date: Wed, 18 Mar 2026 12:03:23 GMT
• Title: Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
• Abstract summary: Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching.<n>We introduce a novel asymmetric training-only framework to bridge this gap without incurring inference costs.<n>Our method consistently establishes a new state-of-the-art across standard 1-16-shot benchmarks.
• Score: 4.273177030613628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity auxiliary Heterogeneous Graph Teacher that operates solely during training. This teacher (i) integrates multi-scale visual patches and text prompts into a unified graph, (ii) performs deep cross-modal reasoning via a Modality-aware Graph Transformer (MGT), and (iii) applies discriminative node filtering to extract high-fidelity class features. Crucially, we employ a cache-aware dual-objective strategy to supervise this relational knowledge directly into the Tip-Adapter's key-value cache, effectively upgrading the prototypes while the graph teacher is discarded at test time. Thus, inference remains identical to Tip-Adapter with zero extra latency or memory. Across standard 1-16-shot benchmarks, our method consistently establishes a new state-of-the-art. Ablations confirm that the auxiliary graph supervision, text-guided reasoning, and node filtering are the essential ingredients for robust few-shot adaptation. Code is available at https://github.com/MR-Sherif/TOGA.git.

Related papers

• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• LOBSTUR: A Local Bootstrap Framework for Tuning Unsupervised Representations in Graph Neural Networks [0.9208007322096533]
  Graph Neural Networks (GNNs) are increasingly used in conjunction with unsupervised learning techniques to learn powerful node representations.<n>We propose a novel framework designed to adapt bootstrapping techniques for unsupervised graph representation learning.
  arXiv  Detail & Related papers  (2025-05-20T19:59:35Z)
• ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models [8.66217922377209]
  Contrastive Language-Image Pretraining (CLIP) has led to its widespread application in various visual downstream tasks.<n>In this paper, we revisit Tip-Adapter from a kernel perspective, showing that caching methods function as local adapters.<n>We propose a global method that learns a proximal regularizer in a reproducing kernel Hilbert space using CLIP as a base learner.
  arXiv  Detail & Related papers  (2025-01-19T21:25:53Z)
• HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter [19.557300178619382]
  We propose a novel Heterogeneous Graph Adapter to achieve tuning VLMs for the downstream tasks. We employ a specific Heterogeneous Graph Neural Network to excavate multi-modality structure knowledge for the downstream tasks. Experimental results on 11 benchmark datasets demonstrate the effectiveness and benefits of the proposed HeGraphAdapter.
  arXiv  Detail & Related papers  (2024-10-10T12:20:58Z)
• p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models [10.713680139939354]
  Vision-Language models (VLMs) pre-trained on large corpora have demonstrated notable success across a range of downstream tasks. PETL has garnered attention as a viable alternative to full fine-tuning. We propose a new adapter architecture, $p$-adapter, which employs $p$-Laplacian message passing in Graph Neural Networks (GNNs)
  arXiv  Detail & Related papers  (2023-12-17T05:30:35Z)
• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph [63.81641578763094]
  adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) We propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge. In particular, the dual knowledge graph is established with two sub-graphs, i.e., a textual knowledge sub-graph, and a visual knowledge sub-graph, where the nodes and edges represent the semantics/classes and their correlations in two modalities, respectively.
  arXiv  Detail & Related papers  (2023-09-24T12:56:40Z)
• Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification [58.06983806317233]
  Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. To enhance CLIP's adaption capability, existing methods proposed to fine-tune additional learnable modules. We propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter.
  arXiv  Detail & Related papers  (2022-07-19T19:12:11Z)
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters [84.88106370842883]
  We show that there is an alternative path to achieve better vision-language models other than prompt tuning.<n>CLIP-Adapter adopts an additional bottleneck layer to learn new features and performs residual-style feature blending.<n> Experiments and extensive ablation studies on various visual classification tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2021-10-09T11:39:30Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)

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.