2021
15 min read
DINO: Emerging Properties in Self-Supervised Vision Transformers
How self-distillation with no labels produces Vision Transformer attention maps that automatically segment objects — without any pixel-level supervision.
ML Paper Reviews - Page 5
Expert analysis and in-depth reviews of machine learning research papers. Covering computer vision, deep learning, and AI innovations with practical insights.
47
Total Reviews
121
Topics
2006-2025
Years Span
Paper Reviews - Page 5
2022
15 min read
MAE: Masked Autoencoders Are Scalable Self-Supervised Learners
How masking 75% of image patches and reconstructing pixels creates a scalable self-supervised learner that trains ViT-H to 87.8% on ImageNet-1K — 3.5× faster than full encoding, no labels required.
2020
15 min read
MoCo: Momentum Contrast for Unsupervised Visual Representation Learning
How a momentum-updated encoder and a dictionary queue make contrastive learning practical — large dictionaries with consistent keys, no large-batch requirement.
2020
15 min read
SimCLR: A Simple Framework for Contrastive Learning
How a simple framework — augmentation, shared encoder, projection head, and contrastive loss — set a new standard for self-supervised visual representation learning.
2024
15 min read
V-JEPA: Learning Video Representations by Predicting in Latent Space
How V-JEPA learns powerful video representations by predicting masked spatiotemporal regions in embedding space rather than reconstructing pixels, achieving state-of-the-art frozen features with superior label efficiency.
2022
15 min read
VICReg: Self-Supervised Learning Without Collapse
How variance, invariance, and covariance regularization enables self-supervised representation learning without negative pairs or momentum encoders.
Showing 25-30 of 47 papers