arXiv Computer Vision
Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Aug 5
Self-Supervised Representation-Guided Generative Dataset Distillation
arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
Hugging Face Trending Papers
Aug 4
Self-Supervised Representation-Guided Generative Dataset Distillation
Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility. Most existing methods target randomly initialized networks, whereas modern vision systems often adapt frozen pretrained encoders with lightweight modules.
arXiv Machine Learning
Jun 9
Optimizing Few-Step Generation with Adaptive Matching Distillation
arXiv:2602. 07345v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force.
Hugging Face Trending Papers
Sep 24
Learning a Flow to Self-Supervised Representations
The paper introduces Flow-Based Distribution Matching (FBDM), a non‑adversarial method that learns self‑supervised representations by aligning images to explicit geometric references through spherical conditional velocity regression. By using an ETF‑inspired reference, FBDM allows more reference components than the flow dimension while maintaining geometric separation, and it incorporates an alignment loss to bring augmented views closer together. Experiments on datasets from CIFAR to ImageNet show that FBDM performs nearly as well as adversarial distribution‑matching methods, achieves a 1.48‑ to 1.83‑fold speedup, and offers a theoretical bound on downstream misclassification rates.
arXiv AI
Sep 10
Precision at Scale: Domain-Specific Datasets On-Demand
arXiv:2407.03463v2 Announce Type: replace-cross Abstract: In the realm of self-supervised learning (SSL), conventional wisdom has gravitated towards the utility of massive, general domain datasets fo...
arXiv AI
4d ago
Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...