Video Self-Distillation for Single-Image Encoders: A Step Toward Physically Plausible Perception
On the map: Knowledge distillation → Detection and dense prediction distillation
Abstract (arXiv)
Self-supervised image encoders such as DINO have recently gained significant interest for learning robust visual features without labels. However, most SSL methods train on static images and miss the temporal cues inherent in videos. We introduce a video-distilled single-image encoder trained to predict the next-frame representation from the current frame. This simple objective injects 3D spatial and temporal priors without optical flow or tracking. When pre-training on a single 2-hour video, our approach raises the mean Intersection-over-Union (mIoU) on ADE20K from 35.0 (DoRA) to 36.4 while remaining a drop-in replacement for image-only pipelines. Our results highlight video self-distillation as a lightweight route to geometry-aware perception an essential ingredient for physically plausible world models and Physical AI.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 11 of its 15 references that are in the map. First posted on arXiv 25 Jul 2025.
Builds on
11 of 15 references.
References · 11
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
- 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
- 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
- 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
- 2023Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videocited by 40
- 2024PooDLe: Pooled and dense self-supervised learning from naturalistic videoscited by 11
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Object-level Self-Distillation for Vision Pretraining
- 2025DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
- 2026Emergent Multi-View Geometry Through Self-Distillation
- 2026Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision
- 2021Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation
- 2023A Simple Recipe for Competitive Low-compute Self supervised Vision Models
- 2026Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
- 2026Self-Improving 4D Perception via Self-Distillation