- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Deep Residual Learning for Image Recognition
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Attention Is All You Need
- Representation Learning with Contrastive Predictive Coding
- A Simple Framework for Contrastive Learning of Visual Representations
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- Bootstrap your own latent: A new approach to self-supervised Learning
- Momentum Contrast for Unsupervised Visual Representation Learning
- Emerging Properties in Self-Supervised Vision Transformers
- Contrastive Multiview Coding
- Exploring Simple Siamese Representation Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- Dataset Distillation by Matching Training Trajectories
- Accelerating Dataset Distillation via Model Augmentation
- Dataset Condensation with Distribution Matching
- Dataset Distillation via the Wasserstein Metric
- Dataset Meta-Learning from Kernel Ridge-Regression
- Dataset Distillation using Neural Feature Regression
- Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
- On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm