Metraipolis › archive › dc_668149c30459
DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations — arXiv:2608.19871
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19871
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:43.693Z
- SHA-256 of the archived text
a66bb10aca6d9c20b3e03c8f5f5a5acb2fd6a3cecb51d414541e9279b0dbabaf- Stable URL of this page
https://metraipolis.com/documento/dc_668149c30459
How to cite
DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations — arXiv:2608.19871 — arXiv (en), https://arxiv.org/abs/2608.19871 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_668149c30459 (Metraipolis archive dc_668149c30459, sha256 a66bb10aca6d9c20b3e03c8f5f5a5acb2fd6a3cecb51d414541e9279b0dbabaf)
BibTeX
@misc{dc668149c30459,
title = {DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations — arXiv:2608.19871},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19871},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_668149c30459; sha256 a66bb10aca6d9c20b3e03c8f5f5a5acb2fd6a3cecb51d414541e9279b0dbabaf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19871. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions. Although recent works achieve impressive performance in CZSL by leveraging large vision-language models, they primarily rely on discriminative representations that may not explicitly preserve the structured relationships between primitive concepts and their compositions. Motivated by the recent success of diffusion-based classifiers and their competitive performance relative to discriminative models, we investigate whether intermediate diffusion representations can provide complementary cues for CZSL. To this end, we propose DIFFCZSL, a diffusion-augmented framework that injects generative priors from pre-trained diffusion models into CLIP-based CZSL pipelines. We extract intermediate diffusion representations and project them into the CLIP embedding space to provide auxiliary supervision on both image and text modalities. Through contrastive alignment between CLIP embeddings and diffusion features during training, our method encourages the embedding geometry toward richer composition-aware semantics, while introducing no additional cost at inference time. Extensive experiments on three public CZSL benchmarks demonstrate consistent improvements over strong CLIP-based baselines under both closed-world and open-world settings. Our results highlight the complementary strengths of generative diffusion representations and discriminative vision-language models for compositional generalization. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.19871 — 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 2026-10-18T12:01:57.725Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).