AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

A Mixed Diet Makes DINO An Omnivorous Vision Encoder

Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson, Ye Xia, Skanda Koppula, Andre Araujo, Joao Carreira, Niloy J. Mitra

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
post-train with cross-modal alignment plus anchoring (Omnivorous)DINOv2 ViT-B/14 · ScanNet cross-modal retrieval (GAP)R@1: 4.6 -> 46.1Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · MOVi cross-modal retrievalR@1: 15.5 -> 86.2Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · ImageNet linear probeaccuracy: 0.801 -> 0.835Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · NYUv2 depth (linear head)RMSE: 0.405 -> 0.377Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · NYUv2 depth (DPT head)RMSE: 0.297 -> 0.297No clear effect
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · iNaturalist k-NNaccuracy: 78.53 -> 77.49Hurt
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · RP2K k-NNaccuracy: 66.83 -> 70.48Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · Zero-shot cross-modal depth, Seg inputRMSE: 1.536 -> 0.532Improved
post-train with Omnivorous alignmentDINOv2 ViT-B/14 · Zero-shot cross-modal depth, NOCS inputRMSE: 1.996 -> 1.075Improved
add modality mixup (alpha_max 0 -> 0.5) (ablation)Omnivorous DINOv2 · Cityscapes segmentation (linear)mIoU: 0.624 -> 0.632Improved
add modality mixup (alpha_max 0 -> 1.0) (ablation)Omnivorous DINOv2 · NYUv2 depth delta1delta1: 0.899 -> 0.891Hurt
train adapter on top instead of fine-tuning final blocks (ablation)Omnivorous DINOv2 · NAVI 3D correspondencePCK@0.0: 29.00 -> 28.15Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy