Metraipolis › archive › dc_2a2117993a85

Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters — arXiv:2611.02769

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02769
License (as archived)
CC0-1.0
Archived
2026-11-03T11:42:37.573Z
SHA-256 of the archived text
89932b45f0e11462cbf6ea309668c4eb04e7bbed9fb72187c3352f2e3c4edff9
Stable URL of this page
https://metraipolis.com/documento/dc_2a2117993a85

How to cite

Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters — arXiv:2611.02769 — arXiv (en), https://arxiv.org/abs/2611.02769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a2117993a85 (Metraipolis archive dc_2a2117993a85, sha256 89932b45f0e11462cbf6ea309668c4eb04e7bbed9fb72187c3352f2e3c4edff9)
BibTeX
@misc{dc2a2117993a85,
  title = {Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters — arXiv:2611.02769},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02769},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a2117993a85; sha256 89932b45f0e11462cbf6ea309668c4eb04e7bbed9fb72187c3352f2e3c4edff9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-task dense prediction seeks a single, coherent representation that supports simultaneously discriminative semantic recognition and regularized geometric/structural inference. For vision foundation models, pretrained semantic invariances conflict with the frequency and smoothness biases of dense objectives; joint fine-tuning and single-route adapters therefore compress competing gradients into one update channel, causing negative transfer and unstable cross-task agreement. We frame this as two-level adaptation: task-generic alignment that preserves priors, and task-aware specialization that resolves late-stage conflicts. Based on this principle, we propose D2MoE , a Mixture of Task Adapters that explicitly factorizes these roles within a frozen DINOv3 backbone. D2MoE introduces Task-Generic Low-Rank Adaptation (TG-LoRA) in attention projections throughout the network to provide a stable, shared adaptation channel, and a Task-Adaptive Mixture of Experts (TA-MoE) injected only at the final attention block of each stage to enact sparse, task-conditioned perturbations of token mixing in a single forward pass. A Semantic Prior Injector further couples multi-level task features with frozen foundation priors to reinforce semantic coherence while preserving boundary and structural fidelity. Experiments across diverse benchmarks substantiate that this structured factorization yields robust multi-task improvements with a small trainable footprint, establishing a principled and scalable route to prior-preserving, foundation-centric multi-task dense perception.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.02769 — 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 2026-11-03T11:06:37.588Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).