# ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling

arXiv: https://arxiv.org/abs/2610.02903 · HTML: https://mlsanity.com/paper/2610.02903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 19 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation](https://mlsanity.com/paper/2410.01680/) (2024)

## Abstract (arXiv)

We study how to consolidate the current VITOK progress into a single multi-teacher distillation recipe that jointly preserves global recognition and dense semantics. Our starting point is an AM-RADIO-style student distilled from SigLIP2 and DINOv3-L, where SigLIP2 supplies strong global semantics and DINOv3-L supplies stronger dense features. The central empirical issue is that the same recipe does not optimize all objectives equally well: changes that improve ImageNet-1K kNN accuracy can still degrade ADE20K segmentation. We summarize a progression of modifications that make this trade-off more explicit and more manageable: split adaptor heads for CLS and patch tokens, asymmetric cosine/MSE losses, initialization from a DINOv3-L checkpoint, teacher reweighting, masked image modeling (MIM), and PHI-S feature balancing. The resulting model reaches 83.2 patch kNN and 85.2 CLS kNN, slightly surpassing the DINOv3-L teacher on ImageNet-1K kNN classification, while PHI-S restores ADE20K performance from 46.5/58.1 to 48.5/61.0 mIoU/mAcc, matching the teacher on this dense benchmark. We also summarize negative results: scaling distillation from ImageNet-1K to ImageNet22K does not consistently help, and naively adding extra teachers such as SAM3 or HOG features introduces interference. Rather than claiming a final recipe, this paper distills the current project state into a compact empirical story and a concrete set of lessons for future iterations.