LSAMD searches a multi-dataset super Ans-Net to extract frequently selected base blocks as learngenes that initialize variable-sized Des-Nets with performance comparable to full pretrain-finetune at lower storage and training cost.
International journal of computer vision , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.
citing papers explorer
-
Learngene Search Across Multiple Datasets for Building Variable-Sized Models
LSAMD searches a multi-dataset super Ans-Net to extract frequently selected base blocks as learngenes that initialize variable-sized Des-Nets with performance comparable to full pretrain-finetune at lower storage and training cost.
-
Revisiting Feature Prediction for Learning Visual Representations from Video
V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.
-
Information theoretic underpinning of self-supervised learning by clustering
SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.