Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
About
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 benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Image Classification | Stanford Cars | Accuracy85.3 | 635 | |
| Image Classification | EuroSAT | Accuracy89.4 | 569 | |
| Image Classification | Flowers102 | Accuracy98.3 | 558 | |
| Image Classification | Food101 | Accuracy87.5 | 457 | |
| Image Classification | SUN397 | Accuracy76.2 | 441 | |
| Image Classification | Caltech101 | Accuracy96.3 | 228 | |
| Image Classification | ImageNet V2 (test) | -- | 216 | |
| Image Classification | ImageNet-A (test) | -- | 175 | |
| Image Classification | OxfordPets | Accuracy93.4 | 160 | |
| Image Classification | ImageNet-Sketch (test) | -- | 153 |