Stay on the Manifold: Hierarchical Bayesian Trajectory-Family Transfer for Sparse-Target Reconstruction and Sampling
cs.CV, cs.AI, stat.ME
Submitted: 2023-07-30
Updated: 2026-11-06
Terminology
Sources
- Few-shot Image Generation with Elastic Weight Consolidation
- Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
- Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
- Prototypical Networks for Few-shot Learning
- Gaussian Prototypical Networks for Few-Shot Learning on Omniglot
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Free Lunch for Few-shot Learning: Distribution Calibration
- Asymmetric Distribution Measure for Few-shot Learning
- Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
- Transductive Few-Shot Classification on the Oblique Manifold
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs