Metraipolis › archive › dc_37c199cb3bea

From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model — arXiv:2610.05711

Source
arXiv
Original
https://arxiv.org/abs/2610.05711
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:13.145Z
SHA-256 of the archived text
139d07fd2b7106aaa13351c171b9cbbbfd05f7c861eaf56c17d4c3a0c07a53ca
Stable URL of this page
https://metraipolis.com/documento/dc_37c199cb3bea

How to cite

From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model — arXiv:2610.05711 — arXiv, https://arxiv.org/abs/2610.05711 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37c199cb3bea (Metraipolis archive dc_37c199cb3bea, sha256 139d07fd2b7106aaa13351c171b9cbbbfd05f7c861eaf56c17d4c3a0c07a53ca)
BibTeX
@misc{dc37c199cb3bea,
  title = {From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model — arXiv:2610.05711},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05711},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37c199cb3bea; sha256 139d07fd2b7106aaa13351c171b9cbbbfd05f7c861eaf56c17d4c3a0c07a53ca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05711. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Strong image generation models are conditioned on class labels, aligned to frozen pretrained encoders, or built on separately trained autoencoders. While effective, generation then depends on supervision or pretraining: labels must be annotated, and encoders or autoencoders pretrained for the target domain. We study joint generative and self-supervised representation learning in a single model, enabling self-conditioned generation without labels or pretrained models. This is challenging because the objectives are mismatched: contrastive learning consumes clean augmented views and favors coarse, invariant semantics, while flow matching consumes noisy images and must preserve the fine detail and spatial layout that contrastive learning discards. We propose SCION (Self-conditioned Generation on Self-supervised representation), whose core is a single pixel-space encoder conditioned on the flow timestep and an embedding. For representation learning, this conditioning embedding is a learned global vector shared across images, with the encoder's [CLS] token yielding the semantic representation trained by the contrastive loss. For generative training, the conditioning embedding is the image's own [CLS] representation, while patch tokens pass through a decoder to predict the image. To sample without a reference image at inference, we jointly learn a prior over the embedding. Gradient-norm balancing and stop-gradient mechanisms enable joint optimization in one run. SCION is self-supervised and self-contained, with no labels or pretrained models. On ImageNet 256x256, with the JiT-B recipe and no representation guidance, SCION reaches 8.92 FID, surpassing class-unconditional iREPA, which aligns to pretrained DINOv2 (46.44), and RCG, which conditions on it (14.27). With JiT-L, SCION achieves 5.89 FID without guidance and 3.47 with representation guidance, outperforming RCG with the ADM recipe (6.24).

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.05711 — 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 2026-10-06T05:27:05.817Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).