AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Progressive Mask Distillation for Self-supervised Video Representation

Kewei Wu, Chong Liang, Zhao Xie, Dan Guo

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining

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
add progressive student distillation (increasing mask ratio across phases) (ablation)MVD base · SSv2 (ViT-B)Top-1 accuracy (%): 72.5 -> 73.0Improved
add difficulty-aware region enhancement (ablation)MVD base · SSv2 (ViT-B)Top-1 accuracy (%): 72.5 -> 72.8Improved
add cross-layer feature alignment (ablation)MVD base · SSv2 (ViT-B)Top-1 accuracy (%): 72.5 -> 72.7Improved
combine all three modules (ablation)MVD base · SSv2 (ViT-B)Top-1 accuracy (%): 72.5 -> 73.7Improved
use four progressive phases instead of a single 90% mask ratio (ablation)PMD pre-training · SSv2 (ViT-B)Top-1 accuracy (%): 73.1 -> 73.7Improved
smoother mask ratio progression (75->80->90 vs 75->85->90) (ablation)PMD pre-training · SSv2 (ViT-B)Top-1 accuracy (%): 73.5 -> 73.6Improved
use higher single mask ratio (75% to 90%) (ablation)single-phase pre-training · SSv2 (ViT-B)Top-1 accuracy (%): 72.7 -> 73.1Improved
add smoothed patch loss and region weights together (ablation)difficulty-aware region enhancement · SSv2 (ViT-B)Top-1 accuracy (%): 72.9 -> 73.7Improved
add both shallow->middle and middle->deep alignment (ablation)cross-layer feature alignment · SSv2 (ViT-B)Top-1 accuracy (%): 73.2 -> 73.7Improved
increase epochs per stage beyond 32 (ablation)difficulty-aware region enhancement · SSv2 (ViT-B)Top-1 accuracy (%): 73.7 -> 73.7No clear effect
increase pre-training epochs from 400 to 800 (ablation)PMD · SSv2 (ViT-B)Top-1 accuracy (%): 73.7 -> 73.7No clear effect
use image plus video teachers instead of one teacher (ablation)PMD · SSv2 (ViT-S student)Top-1 accuracy (%): 73.4 -> 73.7Improved

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