Metraipolis › archive › dc_c3f382c42dcd

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters — arXiv:2603.18101

Source
arXiv (en)
Original
https://arxiv.org/abs/2603.18101
License (as archived)
CC0-1.0
Archived
2026-11-03T18:59:23.638Z
SHA-256 of the archived text
1b4f2baeb3df51d45e083f5dd9cbddcc8946b51c1aa5a0fec5036fbc7affd689
Stable URL of this page
https://metraipolis.com/documento/dc_c3f382c42dcd

How to cite

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters — arXiv:2603.18101 — arXiv (en), https://arxiv.org/abs/2603.18101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3f382c42dcd (Metraipolis archive dc_c3f382c42dcd, sha256 1b4f2baeb3df51d45e083f5dd9cbddcc8946b51c1aa5a0fec5036fbc7affd689)
BibTeX
@misc{dcc3f382c42dcd,
  title = {Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters — arXiv:2603.18101},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2603.18101},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3f382c42dcd; sha256 1b4f2baeb3df51d45e083f5dd9cbddcc8946b51c1aa5a0fec5036fbc7affd689},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2603.18101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.ET, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2603.18101 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:19:24.718Z dalla pagina https://arxiv.org/list/cs.ET/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).